Federated Learning With Differential Privacy: Algorithms and Performance Analysis
Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients' private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in dee...
Saved in:
| Published in: | IEEE transactions on information forensics and security Vol. 15; pp. 3454 - 3469 |
|---|---|
| Main Authors: | , , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
IEEE
2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 1556-6013, 1556-6021 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients' private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in deep neural networks. In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noise is added to parameters at the clients' side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noise. Then we develop a theoretical convergence bound on the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three key properties: 1) there is a tradeoff between convergence performance and privacy protection levels, i.e., better convergence performance leads to a lower protection level; 2) given a fixed privacy protection level, increasing the number <inline-formula> <tex-math notation="LaTeX">N </tex-math></inline-formula> of overall clients participating in FL can improve the convergence performance; and 3) there is an optimal number aggregation times (communication rounds) in terms of convergence performance for a given protection level. Furthermore, we propose a <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula>-client random scheduling strategy, where <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula> (<inline-formula> <tex-math notation="LaTeX">1\leq K< N </tex-math></inline-formula>) clients are randomly selected from the <inline-formula> <tex-math notation="LaTeX">N </tex-math></inline-formula> overall clients to participate in each aggregation. We also develop a corresponding convergence bound for the loss function in this case and the <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula>-client random scheduling strategy also retains the above three properties. Moreover, we find that there is an optimal <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula> that achieves the best convergence performance at a fixed privacy level. Evaluations demonstrate that our theoretical results are consistent with simulations, thereby facilitating the design of various privacy-preserving FL algorithms with different tradeoff requirements on convergence performance and privacy levels. |
|---|---|
| AbstractList | Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients' private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in deep neural networks. In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noise is added to parameters at the clients' side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noise. Then we develop a theoretical convergence bound on the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three key properties: 1) there is a tradeoff between convergence performance and privacy protection levels, i.e., better convergence performance leads to a lower protection level; 2) given a fixed privacy protection level, increasing the number <inline-formula> <tex-math notation="LaTeX">N </tex-math></inline-formula> of overall clients participating in FL can improve the convergence performance; and 3) there is an optimal number aggregation times (communication rounds) in terms of convergence performance for a given protection level. Furthermore, we propose a <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula>-client random scheduling strategy, where <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula> (<inline-formula> <tex-math notation="LaTeX">1\leq K< N </tex-math></inline-formula>) clients are randomly selected from the <inline-formula> <tex-math notation="LaTeX">N </tex-math></inline-formula> overall clients to participate in each aggregation. We also develop a corresponding convergence bound for the loss function in this case and the <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula>-client random scheduling strategy also retains the above three properties. Moreover, we find that there is an optimal <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula> that achieves the best convergence performance at a fixed privacy level. Evaluations demonstrate that our theoretical results are consistent with simulations, thereby facilitating the design of various privacy-preserving FL algorithms with different tradeoff requirements on convergence performance and privacy levels. Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in deep neural networks. In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noise is added to parameters at the clients’ side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noise. Then we develop a theoretical convergence bound on the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three key properties: 1) there is a tradeoff between convergence performance and privacy protection levels, i.e., better convergence performance leads to a lower protection level; 2) given a fixed privacy protection level, increasing the number [Formula Omitted] of overall clients participating in FL can improve the convergence performance; and 3) there is an optimal number aggregation times (communication rounds) in terms of convergence performance for a given protection level. Furthermore, we propose a [Formula Omitted]-client random scheduling strategy, where [Formula Omitted] ([Formula Omitted]) clients are randomly selected from the [Formula Omitted] overall clients to participate in each aggregation. We also develop a corresponding convergence bound for the loss function in this case and the [Formula Omitted]-client random scheduling strategy also retains the above three properties. Moreover, we find that there is an optimal [Formula Omitted] that achieves the best convergence performance at a fixed privacy level. Evaluations demonstrate that our theoretical results are consistent with simulations, thereby facilitating the design of various privacy-preserving FL algorithms with different tradeoff requirements on convergence performance and privacy levels. |
| Author | Li, Jun Ma, Chuan Quek, Tony Q. S. Ding, Ming Jin, Shi Vincent Poor, H. Yang, Howard H. Wei, Kang Farokhi, Farhad |
| Author_xml | – sequence: 1 givenname: Kang surname: Wei fullname: Wei, Kang email: kang.wei@njust.edu.cn organization: School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China – sequence: 2 givenname: Jun surname: Li fullname: Li, Jun email: jun.li@njust.edu.cn organization: School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China – sequence: 3 givenname: Ming surname: Ding fullname: Ding, Ming email: ming.ding@data61.csiro.au organization: CSIRO Data61, Sydney, NSW, Australia – sequence: 4 givenname: Chuan surname: Ma fullname: Ma, Chuan email: chuan.ma@njust.edu.cn organization: School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China – sequence: 5 givenname: Howard H. surname: Yang fullname: Yang, Howard H. email: howard_yang@sutd.edu.sg organization: Singapore University of Technology and Design, Singapore – sequence: 6 givenname: Farhad surname: Farokhi fullname: Farokhi, Farhad email: ffarokhi@unimelb.edu.au organization: CSIRO's Data61, Melbourne, VIC, Australia – sequence: 7 givenname: Shi surname: Jin fullname: Jin, Shi email: jinshi@seu.edu.cn organization: National Mobile Communications Research Laboratory, Southeast University, Nanjing, China – sequence: 8 givenname: Tony Q. S. surname: Quek fullname: Quek, Tony Q. S. email: tonyquek@sutd.edu.sg organization: Singapore University of Technology and Design, Singapore – sequence: 9 givenname: H. surname: Vincent Poor fullname: Vincent Poor, H. organization: Department of Electrical Engineering, Princeton University, Princeton, NJ |
| BookMark | eNp9kFFLwzAQx4NMcJt-APEl4HNn0jRp69uYTgcDJ058LNf2MjO6dCaZsG9vx4YPPvh0x93_dxy_AenZ1iIh15yNOGf53XI2fRvFLGajOM8ymcoz0udSqkixmPd-ey4uyMD7NWNJwlXWJ69TrNFBwJrOEZw1dkU_TPikD0ZrdGiDgYYunPmGan9Px82qdd164ynYmi7Q6dZtwFZIxxaavTf-kpxraDxeneqQvE8fl5PnaP7yNJuM51ElhApRpZXMyxqEgFoyyPIsTRDKNEnLMlNQ1VxDFpdKp7kGoUVVirpUGQOJqebdYEhuj3e3rv3aoQ_Fut257glfxAlPpBBpnHSp9JiqXOu9Q11UJkAwrQ0OTFNwVhz8FQd_xcFfcfLXkfwPuXVmA27_L3NzZAwi_uZzpvK8e-gHEyx-vw |
| CODEN | ITIFA6 |
| CitedBy_id | crossref_primary_10_1007_s10586_024_04850_4 crossref_primary_10_3390_s20216230 crossref_primary_10_1016_j_neucom_2024_127290 crossref_primary_10_1109_TWC_2024_3457591 crossref_primary_10_1016_j_neunet_2023_04_007 crossref_primary_10_1109_TII_2021_3126728 crossref_primary_10_1145_3729216 crossref_primary_10_1109_TCSS_2022_3225096 crossref_primary_10_1109_TCC_2025_3540023 crossref_primary_10_1016_j_compeleceng_2023_108661 crossref_primary_10_1109_COMST_2024_3434510 crossref_primary_10_1016_j_comcom_2023_11_022 crossref_primary_10_1109_TIFS_2023_3240291 crossref_primary_10_1109_JIOT_2024_3405939 crossref_primary_10_1109_TWC_2024_3479149 crossref_primary_10_3390_app14135361 crossref_primary_10_1007_s10922_023_09782_9 crossref_primary_10_1016_j_jisa_2025_104224 crossref_primary_10_1109_JIOT_2024_3357779 crossref_primary_10_1109_TCCN_2023_3284548 crossref_primary_10_1109_TASE_2025_3589764 crossref_primary_10_1109_JIOT_2021_3111088 crossref_primary_10_1109_TCSS_2021_3134463 crossref_primary_10_1109_TSC_2023_3332102 crossref_primary_10_1016_j_future_2024_07_035 crossref_primary_10_1155_2022_5031112 crossref_primary_10_1093_jamia_ocad170 crossref_primary_10_1016_j_csbj_2024_12_001 crossref_primary_10_1016_j_engappai_2025_110078 crossref_primary_10_3390_e25111551 crossref_primary_10_1007_s11277_024_11372_0 crossref_primary_10_1007_s13042_025_02612_1 crossref_primary_10_1016_j_compag_2024_109001 crossref_primary_10_1109_ACCESS_2022_3229124 crossref_primary_10_1109_TGRS_2024_3386978 crossref_primary_10_1109_TNET_2024_3438462 crossref_primary_10_1016_j_rcim_2024_102779 crossref_primary_10_1016_j_iswa_2025_200553 crossref_primary_10_1109_ACCESS_2020_3030888 crossref_primary_10_3390_en18174682 crossref_primary_10_1016_j_eswa_2024_126228 crossref_primary_10_3390_app14198959 crossref_primary_10_1109_TNSE_2023_3297880 crossref_primary_10_1016_j_cose_2022_102993 crossref_primary_10_1109_JBHI_2022_3185418 crossref_primary_10_1109_TSG_2024_3503604 crossref_primary_10_1109_TIFS_2022_3232955 crossref_primary_10_1109_TIFS_2025_3593357 crossref_primary_10_1016_j_jisa_2022_103309 crossref_primary_10_1109_TMC_2024_3364372 crossref_primary_10_1109_TDSC_2023_3325889 crossref_primary_10_1109_TIM_2025_3556830 crossref_primary_10_3390_s24051364 crossref_primary_10_1016_j_asoc_2025_113800 crossref_primary_10_1109_MWC_005_2100435 crossref_primary_10_1016_j_ject_2024_12_003 crossref_primary_10_1016_j_neucom_2024_128166 crossref_primary_10_1109_TAI_2024_3419757 crossref_primary_10_1109_TKDE_2024_3454328 crossref_primary_10_3390_jsan14040083 crossref_primary_10_1109_TIFS_2022_3186739 crossref_primary_10_1016_j_inffus_2025_103292 crossref_primary_10_1109_TBDATA_2022_3227326 crossref_primary_10_3390_e26070590 crossref_primary_10_1007_s12083_025_01962_5 crossref_primary_10_1109_JIOT_2021_3127886 crossref_primary_10_1109_JIOT_2023_3293230 crossref_primary_10_1109_ACCESS_2024_3454211 crossref_primary_10_1109_TII_2022_3183465 crossref_primary_10_1007_s10773_021_04867_0 crossref_primary_10_3390_ijerph20156539 crossref_primary_10_1109_ACCESS_2024_3454690 crossref_primary_10_1016_j_aej_2025_03_034 crossref_primary_10_1109_JIOT_2021_3079472 crossref_primary_10_1109_ACCESS_2025_3540878 crossref_primary_10_1109_JIOT_2024_3460349 crossref_primary_10_1109_TNET_2024_3351864 crossref_primary_10_3389_fpsyt_2022_993289 crossref_primary_10_1109_TMC_2025_3564301 crossref_primary_10_1155_2022_1657558 crossref_primary_10_1007_s00778_024_00865_w crossref_primary_10_1016_j_future_2024_06_023 crossref_primary_10_1109_ACCESS_2022_3175219 crossref_primary_10_1109_JSTSP_2022_3162109 crossref_primary_10_1145_3589264 crossref_primary_10_1007_s10844_023_00797_x crossref_primary_10_1109_TMC_2023_3237636 crossref_primary_10_1038_s41598_024_70025_1 crossref_primary_10_1109_TCYB_2025_3571953 crossref_primary_10_1109_TNSE_2025_3545912 crossref_primary_10_26599_TST_2023_9010007 crossref_primary_10_3390_s23073570 crossref_primary_10_1109_TDSC_2025_3559108 crossref_primary_10_1109_TII_2022_3170156 crossref_primary_10_1016_j_neunet_2025_107135 crossref_primary_10_1016_j_future_2022_12_026 crossref_primary_10_1109_JIOT_2021_3072611 crossref_primary_10_1109_JIOT_2023_3285868 crossref_primary_10_1109_TDSC_2025_3574745 crossref_primary_10_14778_3748191_3748213 crossref_primary_10_1145_3682068 crossref_primary_10_1145_3433638 crossref_primary_10_1109_JIOT_2024_3408149 crossref_primary_10_1109_COMST_2024_3399612 crossref_primary_10_3390_electronics13224545 crossref_primary_10_1109_TDSC_2022_3218793 crossref_primary_10_1109_ACCESS_2024_3359272 crossref_primary_10_1007_s40747_025_01937_2 crossref_primary_10_1109_ACCESS_2024_3429285 crossref_primary_10_1016_j_ins_2023_03_033 crossref_primary_10_1109_TCE_2025_3533750 crossref_primary_10_1016_j_cosrev_2023_100595 crossref_primary_10_1109_TDSC_2024_3362534 crossref_primary_10_1109_TBDATA_2022_3177170 crossref_primary_10_1145_3591362 crossref_primary_10_3390_electronics11234007 crossref_primary_10_3390_electronics14051024 crossref_primary_10_1145_3650028 crossref_primary_10_1145_3707651 crossref_primary_10_1109_TAC_2024_3519938 crossref_primary_10_1109_JIOT_2024_3370991 crossref_primary_10_1016_j_asoc_2025_112925 crossref_primary_10_1109_JSEN_2023_3285618 crossref_primary_10_1109_TSP_2023_3316590 crossref_primary_10_1109_COMST_2024_3446585 crossref_primary_10_1109_TII_2021_3055283 crossref_primary_10_1109_TWC_2024_3453392 crossref_primary_10_1016_j_ins_2023_119808 crossref_primary_10_1109_JIOT_2022_3229122 crossref_primary_10_1109_ACCESS_2023_3235389 crossref_primary_10_1016_j_iot_2024_101344 crossref_primary_10_1109_TMC_2023_3309633 crossref_primary_10_1007_s10115_025_02339_z crossref_primary_10_1109_TBDATA_2025_3527202 crossref_primary_10_1109_JSTSP_2024_3485878 crossref_primary_10_1109_TPDS_2024_3413751 crossref_primary_10_1016_j_pmcj_2025_102021 crossref_primary_10_1007_s10462_024_10797_0 crossref_primary_10_1109_TDSC_2023_3234599 crossref_primary_10_1109_LCOMM_2022_3167088 crossref_primary_10_1109_JIOT_2025_3579583 crossref_primary_10_1109_JIOT_2023_3238038 crossref_primary_10_1080_10556788_2023_2280056 crossref_primary_10_1109_TDSC_2024_3364371 crossref_primary_10_1109_TIFS_2025_3602314 crossref_primary_10_1109_TDSC_2023_3346183 crossref_primary_10_3390_app15126918 crossref_primary_10_1007_s11704_023_2283_x crossref_primary_10_1093_comjnl_bxae081 crossref_primary_10_1109_ACCESS_2020_3034602 crossref_primary_10_1109_TIFS_2023_3340994 crossref_primary_10_1007_s10586_024_04810_y crossref_primary_10_3390_bdcc8110162 crossref_primary_10_1007_s10479_023_05477_1 crossref_primary_10_1016_j_future_2025_107848 crossref_primary_10_1109_TSUSC_2024_3381812 crossref_primary_10_1155_2021_8967819 crossref_primary_10_1145_3679013 crossref_primary_10_1109_TMC_2025_3569669 crossref_primary_10_1145_3701740 crossref_primary_10_1016_j_inffus_2024_102290 crossref_primary_10_1016_j_jisa_2025_103986 crossref_primary_10_1055_s_0041_1740630 crossref_primary_10_1109_JSTSP_2022_3156756 crossref_primary_10_1109_TII_2021_3073925 crossref_primary_10_1016_j_future_2024_05_048 crossref_primary_10_3390_s25030967 crossref_primary_10_1109_TCE_2023_3338464 crossref_primary_10_1109_JIOT_2024_3356250 crossref_primary_10_1109_TSIPN_2025_3572292 crossref_primary_10_1109_MNET_2024_3442880 crossref_primary_10_1109_TIM_2023_3346494 crossref_primary_10_1109_TDSC_2025_3532957 crossref_primary_10_1109_JSAC_2022_3213347 crossref_primary_10_1016_j_jisa_2025_103992 crossref_primary_10_1109_COMST_2022_3221119 crossref_primary_10_1109_TSP_2023_3317644 crossref_primary_10_1016_j_jobe_2024_111712 crossref_primary_10_1109_TNET_2024_3422264 crossref_primary_10_1121_10_0010070 crossref_primary_10_1109_TNSE_2024_3488719 crossref_primary_10_1109_ACCESS_2021_3130610 crossref_primary_10_1109_TIFS_2024_3402361 crossref_primary_10_3390_e24030430 crossref_primary_10_1145_3678181 crossref_primary_10_1007_s10994_024_06541_y crossref_primary_10_1016_j_ipm_2022_103211 crossref_primary_10_1109_TCE_2024_3517739 crossref_primary_10_1109_TIFS_2025_3575582 crossref_primary_10_3233_IDT_230104 crossref_primary_10_1109_JIOT_2022_3194813 crossref_primary_10_1109_MWC_007_2200101 crossref_primary_10_2166_wqrj_2024_045 crossref_primary_10_1007_s11633_023_1449_1 crossref_primary_10_1109_TAI_2021_3139055 crossref_primary_10_1109_JIOT_2022_3162826 crossref_primary_10_1109_TSC_2023_3332955 crossref_primary_10_3390_app14188490 crossref_primary_10_1016_j_eswa_2023_120266 crossref_primary_10_1016_j_future_2020_10_007 crossref_primary_10_1109_ACCESS_2023_3325396 crossref_primary_10_1109_TCSS_2024_3361465 crossref_primary_10_1007_s11227_024_06642_4 crossref_primary_10_1109_JIOT_2022_3171767 crossref_primary_10_1109_TMC_2024_3414138 crossref_primary_10_1109_TWC_2024_3446669 crossref_primary_10_1109_TIT_2022_3216793 crossref_primary_10_3390_e25030485 crossref_primary_10_1109_JSAC_2021_3126052 crossref_primary_10_1142_S0129065725500601 crossref_primary_10_1109_TKDE_2023_3241442 crossref_primary_10_1109_ACCESS_2022_3183224 crossref_primary_10_1109_MNET_2024_3371535 crossref_primary_10_1016_j_eswa_2023_122210 crossref_primary_10_1016_j_neucom_2023_126791 crossref_primary_10_1109_TMC_2025_3564390 crossref_primary_10_1109_TIFS_2023_3255171 crossref_primary_10_1109_COMST_2022_3208196 crossref_primary_10_1016_j_jisa_2023_103460 crossref_primary_10_1002_cpe_70072 crossref_primary_10_1016_j_cose_2023_103562 crossref_primary_10_1016_j_iotcps_2023_04_001 crossref_primary_10_3390_electronics14061218 crossref_primary_10_1109_TIFS_2024_3402319 crossref_primary_10_1007_s10994_025_06836_8 crossref_primary_10_1109_TII_2022_3214998 crossref_primary_10_1109_JIOT_2024_3445964 crossref_primary_10_3390_jcp2040044 crossref_primary_10_1007_s10586_024_04558_5 crossref_primary_10_1109_JIOT_2024_3421991 crossref_primary_10_1109_JIOT_2024_3514637 crossref_primary_10_1016_j_trpro_2023_11_819 crossref_primary_10_1109_TIFS_2023_3293417 crossref_primary_10_1109_TIFS_2023_3329441 crossref_primary_10_1016_j_ins_2022_05_083 crossref_primary_10_1109_ACCESS_2023_3287195 crossref_primary_10_1145_3560816 crossref_primary_10_1016_j_jisa_2024_103890 crossref_primary_10_1007_s10462_022_10141_4 crossref_primary_10_1109_JIOT_2023_3277632 crossref_primary_10_1007_s11432_024_4337_1 crossref_primary_10_1109_ACCESS_2023_3257562 crossref_primary_10_1016_j_future_2023_01_019 crossref_primary_10_1007_s11227_022_04745_4 crossref_primary_10_1016_j_comnet_2025_111043 crossref_primary_10_1109_TWC_2022_3225812 crossref_primary_10_3390_make7010013 crossref_primary_10_1016_j_enbuild_2024_115164 crossref_primary_10_1016_j_eswa_2025_127003 crossref_primary_10_1016_j_inffus_2023_102198 crossref_primary_10_1016_j_cmpb_2023_107706 crossref_primary_10_1109_TNSM_2024_3393969 crossref_primary_10_1109_LCOMM_2021_3121297 crossref_primary_10_1016_j_bspc_2024_106577 crossref_primary_10_1145_3745025 crossref_primary_10_1109_TWC_2023_3344137 crossref_primary_10_1007_s10207_023_00754_3 crossref_primary_10_1016_j_compeleceng_2025_110515 crossref_primary_10_1109_TP_2025_3531838 crossref_primary_10_1007_s11276_021_02870_1 crossref_primary_10_1016_j_knosys_2023_111356 crossref_primary_10_3390_jimaging8090233 crossref_primary_10_1016_j_future_2024_04_051 crossref_primary_10_1016_j_knosys_2021_107532 crossref_primary_10_1109_JIOT_2024_3354942 crossref_primary_10_1109_TIFS_2025_3552033 crossref_primary_10_1109_TNNLS_2024_3370297 crossref_primary_10_1109_TNSE_2025_3568030 crossref_primary_10_1109_TIFS_2024_3524160 crossref_primary_10_1109_TCE_2024_3510694 crossref_primary_10_1145_3745032 crossref_primary_10_1109_JIOT_2021_3095077 crossref_primary_10_1155_2020_8845038 crossref_primary_10_1016_j_future_2025_108061 crossref_primary_10_1109_JIOT_2021_3050163 crossref_primary_10_1016_j_ins_2024_121223 crossref_primary_10_3390_electronics12163382 crossref_primary_10_3389_fcomp_2024_1494174 crossref_primary_10_1109_TDSC_2025_3567564 crossref_primary_10_1109_TSMC_2025_3550524 crossref_primary_10_1145_3554980 crossref_primary_10_1109_TIFS_2024_3368879 crossref_primary_10_1007_s10586_024_04957_8 crossref_primary_10_1109_TIFS_2025_3542244 crossref_primary_10_1109_OJCOMS_2025_3566464 crossref_primary_10_1016_j_ibmed_2025_100283 crossref_primary_10_1109_TKDE_2024_3349863 crossref_primary_10_1016_j_eswa_2025_128483 crossref_primary_10_1109_JIOT_2023_3264259 crossref_primary_10_1007_s10586_022_03813_x crossref_primary_10_1007_s11042_024_20476_5 crossref_primary_10_1109_ACCESS_2024_3472467 crossref_primary_10_1109_TIFS_2023_3302161 crossref_primary_10_1016_j_ipm_2022_103167 crossref_primary_10_1109_JIOT_2024_3439599 crossref_primary_10_1109_TNSM_2023_3263831 crossref_primary_10_1109_TMC_2024_3445957 crossref_primary_10_1109_JIOT_2024_3383226 crossref_primary_10_1145_3702325 crossref_primary_10_1109_JIOT_2024_3427132 crossref_primary_10_1109_TIFS_2021_3097822 crossref_primary_10_1109_TNET_2024_3481437 crossref_primary_10_1016_j_cosrev_2024_100697 crossref_primary_10_32604_cmes_2024_030084 crossref_primary_10_1109_MSP_2021_3125282 crossref_primary_10_1109_TSC_2024_3376247 crossref_primary_10_1109_JIOT_2023_3308170 crossref_primary_10_1109_TKDE_2024_3379001 crossref_primary_10_1007_s10462_024_10766_7 crossref_primary_10_1109_TII_2021_3107783 crossref_primary_10_1109_TDSC_2022_3233580 crossref_primary_10_1109_TPDS_2022_3195207 crossref_primary_10_1109_TIFS_2025_3526050 crossref_primary_10_1109_TMC_2024_3484493 crossref_primary_10_26599_BDMA_2024_9020053 crossref_primary_10_1016_j_knosys_2024_112516 crossref_primary_10_1109_JIOT_2024_3385479 crossref_primary_10_1145_3634686 crossref_primary_10_1109_TPDS_2022_3217271 crossref_primary_10_1097_CM9_0000000000003302 crossref_primary_10_1109_TC_2025_3584272 crossref_primary_10_1109_TIFS_2024_3486611 crossref_primary_10_3390_app14156824 crossref_primary_10_1016_j_adhoc_2025_103962 crossref_primary_10_1007_s11042_023_16543_y crossref_primary_10_1109_ACCESS_2024_3413069 crossref_primary_10_1109_JBHI_2022_3192648 crossref_primary_10_1145_3725847 crossref_primary_10_1016_j_future_2023_10_013 crossref_primary_10_1111_exsy_70087 crossref_primary_10_3390_electronics14050990 crossref_primary_10_1109_TSIPN_2023_3325963 crossref_primary_10_3390_app15062914 crossref_primary_10_1109_TIFS_2024_3361813 crossref_primary_10_3390_s22165983 crossref_primary_10_1016_j_eswa_2025_128273 crossref_primary_10_1109_TSC_2025_3562359 crossref_primary_10_1016_j_neucom_2021_07_098 crossref_primary_10_1109_JIOT_2023_3289546 crossref_primary_10_3390_app14177993 crossref_primary_10_1016_j_future_2023_10_014 crossref_primary_10_1109_TIM_2023_3328074 crossref_primary_10_1145_3677390 crossref_primary_10_1016_j_inffus_2022_07_024 crossref_primary_10_1016_j_procs_2023_01_177 crossref_primary_10_1109_COMST_2020_3024783 crossref_primary_10_1016_j_engappai_2024_109216 crossref_primary_10_1109_JIOT_2021_3132056 crossref_primary_10_1109_TIFS_2022_3221899 crossref_primary_10_1007_s11277_024_11477_6 crossref_primary_10_1109_TCE_2024_3376561 crossref_primary_10_1145_3460427 crossref_primary_10_1016_j_compeleceng_2024_109893 crossref_primary_10_1145_3501814 crossref_primary_10_1109_TMC_2025_3538871 crossref_primary_10_1108_IJWIS_04_2024_0120 crossref_primary_10_1016_j_eswa_2025_129379 crossref_primary_10_1109_JPROC_2021_3119950 crossref_primary_10_1109_TKDE_2021_3140131 crossref_primary_10_1016_j_egyai_2025_100521 crossref_primary_10_1109_LSP_2024_3431951 crossref_primary_10_1016_j_cose_2023_103278 crossref_primary_10_1007_s10586_024_04759_y crossref_primary_10_1016_j_inffus_2025_103657 crossref_primary_10_1109_ACCESS_2025_3576261 crossref_primary_10_1109_TWC_2023_3347697 crossref_primary_10_1016_j_jnca_2023_103812 crossref_primary_10_1109_JIOT_2024_3482703 crossref_primary_10_1016_j_comnet_2025_111200 crossref_primary_10_1109_ACCESS_2024_3493112 crossref_primary_10_1109_TCOMM_2021_3078783 crossref_primary_10_1007_s42952_023_00249_w crossref_primary_10_1016_j_compeleceng_2024_109643 crossref_primary_10_1016_j_csi_2023_103723 crossref_primary_10_1145_3501808 crossref_primary_10_1016_j_csi_2023_103720 crossref_primary_10_1016_j_neucom_2024_128653 crossref_primary_10_1109_JIOT_2022_3151982 crossref_primary_10_1109_TII_2022_3156645 crossref_primary_10_1109_TIFS_2023_3318944 crossref_primary_10_1016_j_eswa_2023_123006 crossref_primary_10_1109_TDSC_2025_3567301 crossref_primary_10_1109_TIFS_2022_3174394 crossref_primary_10_1109_TPAMI_2023_3322785 crossref_primary_10_1109_TETCI_2024_3370005 crossref_primary_10_1109_LWC_2022_3141792 crossref_primary_10_1109_JIOT_2025_3561262 crossref_primary_10_1016_j_ins_2024_120519 crossref_primary_10_1109_TNSE_2022_3217923 crossref_primary_10_1109_TDSC_2025_3526840 crossref_primary_10_1016_j_arcontrol_2023_100913 crossref_primary_10_1186_s13635_025_00203_9 crossref_primary_10_1109_TMC_2024_3466227 crossref_primary_10_1109_TAI_2024_3446759 crossref_primary_10_1038_s41598_024_72894_y crossref_primary_10_1109_TAC_2023_3348158 crossref_primary_10_3390_math11183807 crossref_primary_10_1016_j_jss_2025_112442 crossref_primary_10_1080_09540091_2023_2299103 crossref_primary_10_1109_TII_2022_3170348 crossref_primary_10_3390_s24248028 crossref_primary_10_1109_JIOT_2022_3154605 crossref_primary_10_1109_TSUSC_2024_3441658 crossref_primary_10_1109_TIFS_2022_3176191 crossref_primary_10_1109_TMC_2025_3574784 crossref_primary_10_1016_j_cose_2021_102402 crossref_primary_10_1109_TITS_2023_3324962 crossref_primary_10_1109_MNET_2024_3494764 crossref_primary_10_1007_s10207_022_00607_5 crossref_primary_10_1109_MCE_2021_3059958 crossref_primary_10_1109_JIOT_2023_3340880 crossref_primary_10_1109_TC_2022_3230904 crossref_primary_10_1016_j_neucom_2023_127043 crossref_primary_10_1109_TMC_2021_3056991 crossref_primary_10_1145_3606274_3606280 crossref_primary_10_1016_j_dsp_2024_104589 crossref_primary_10_1109_TSP_2021_3121632 crossref_primary_10_1109_TIFS_2024_3433537 crossref_primary_10_1007_s10115_022_01664_x crossref_primary_10_1109_JIOT_2023_3324801 crossref_primary_10_1109_OJCOMS_2024_3521651 crossref_primary_10_1016_j_jisa_2025_104161 crossref_primary_10_32604_cmc_2023_041897 crossref_primary_10_1109_ACCESS_2022_3202008 crossref_primary_10_1080_10408398_2022_2103086 crossref_primary_10_1109_TIFS_2022_3222935 crossref_primary_10_1016_j_ins_2023_119235 crossref_primary_10_1371_journal_pone_0301897 crossref_primary_10_1109_JIOT_2024_3402250 crossref_primary_10_1007_s40012_022_00351_0 crossref_primary_10_1016_j_sysarc_2022_102555 crossref_primary_10_1016_j_apenergy_2025_126177 crossref_primary_10_1109_TSC_2024_3451187 crossref_primary_10_1109_ACCESS_2025_3583436 crossref_primary_10_1002_sim_10290 crossref_primary_10_1007_s11227_025_07322_7 crossref_primary_10_1109_JSTSP_2022_3161786 crossref_primary_10_1109_TETCI_2025_3540420 crossref_primary_10_1016_j_ins_2025_121901 crossref_primary_10_1016_j_knosys_2023_111166 crossref_primary_10_1109_TIFS_2024_3515814 crossref_primary_10_1186_s13634_023_01049_4 crossref_primary_10_3390_electronics13173538 crossref_primary_10_1186_s42400_024_00232_w crossref_primary_10_1109_JIOT_2024_3391923 crossref_primary_10_1109_TCCN_2022_3196009 crossref_primary_10_1016_j_comcom_2023_05_004 crossref_primary_10_1016_j_cose_2025_104592 crossref_primary_10_3390_info16010008 crossref_primary_10_3390_math13071096 crossref_primary_10_1109_ACCESS_2023_3263533 crossref_primary_10_1109_TDSC_2022_3168556 crossref_primary_10_1016_j_asoc_2021_107235 crossref_primary_10_1002_cpe_7827 crossref_primary_10_1109_TVT_2021_3132226 crossref_primary_10_1016_j_dcan_2025_07_006 crossref_primary_10_1109_TSC_2024_3355188 crossref_primary_10_1109_TBDATA_2024_3403388 crossref_primary_10_32604_cmc_2024_049215 crossref_primary_10_1109_TNSM_2024_3414417 crossref_primary_10_1109_TNSM_2025_3564387 crossref_primary_10_1145_3724113 crossref_primary_10_1109_JETCAS_2024_3463738 crossref_primary_10_1109_TFUZZ_2024_3445468 crossref_primary_10_1109_TMC_2024_3396993 crossref_primary_10_3390_computers13110277 crossref_primary_10_1109_TPAMI_2022_3195956 crossref_primary_10_1145_3555803 crossref_primary_10_1007_s10791_025_09676_1 crossref_primary_10_1109_TWC_2024_3487986 crossref_primary_10_1145_3690768 crossref_primary_10_1109_TDSC_2023_3336977 crossref_primary_10_1016_j_jnca_2025_104201 crossref_primary_10_1109_TKDE_2023_3295601 crossref_primary_10_1109_TCSS_2024_3406528 crossref_primary_10_1109_JSAC_2023_3310060 crossref_primary_10_1109_TPDS_2023_3273490 crossref_primary_10_4018_IJITSA_383947 crossref_primary_10_1016_j_neucom_2021_08_062 crossref_primary_10_1109_TIFS_2023_3265535 crossref_primary_10_1109_JIOT_2021_3102030 crossref_primary_10_1016_j_fsidi_2021_301314 crossref_primary_10_1109_TSP_2023_3244092 crossref_primary_10_1109_JIOT_2025_3558910 crossref_primary_10_1049_cmu2_12722 crossref_primary_10_1109_JIOT_2022_3188833 crossref_primary_10_1109_TCCN_2021_3076167 crossref_primary_10_1109_JIOT_2023_3283853 crossref_primary_10_1109_TWC_2024_3384957 crossref_primary_10_1109_JPROC_2023_3306773 crossref_primary_10_1109_ACCESS_2020_3036322 crossref_primary_10_1167_iovs_65_6_21 crossref_primary_10_3390_telecom6030060 crossref_primary_10_1016_j_inffus_2024_102420 crossref_primary_10_1145_3701039 crossref_primary_10_1145_3687124 crossref_primary_10_1016_j_sysarc_2022_102754 crossref_primary_10_1109_ACCESS_2024_3429205 crossref_primary_10_1109_JIOT_2023_3288078 crossref_primary_10_1016_j_cose_2022_102966 crossref_primary_10_1109_TGRS_2025_3537085 crossref_primary_10_1016_j_neucom_2024_128019 crossref_primary_10_1016_j_knosys_2025_113741 crossref_primary_10_1016_j_rineng_2025_105456 crossref_primary_10_1109_TDSC_2022_3215574 crossref_primary_10_1109_TIFS_2022_3206420 crossref_primary_10_1007_s10586_024_04289_7 crossref_primary_10_1007_s11432_024_4254_5 crossref_primary_10_1007_s10586_024_04837_1 crossref_primary_10_1109_ACCESS_2024_3432610 crossref_primary_10_1109_JIOT_2021_3057419 crossref_primary_10_3390_electronics11091449 crossref_primary_10_32628_IJSRST24116166 crossref_primary_10_1093_bib_bbae641 crossref_primary_10_1109_TNSM_2022_3184992 crossref_primary_10_3390_math11051091 crossref_primary_10_1109_TGRS_2023_3320044 crossref_primary_10_1109_TIFS_2024_3522792 crossref_primary_10_1186_s12911_024_02563_7 crossref_primary_10_3390_fi16110415 crossref_primary_10_1109_TSUSC_2024_3403427 crossref_primary_10_1097_RLU_0000000000004194 crossref_primary_10_1109_ACCESS_2024_3387453 crossref_primary_10_1002_cpe_7901 crossref_primary_10_3390_electronics13132620 crossref_primary_10_1109_TMC_2021_3093316 crossref_primary_10_1145_3744745 crossref_primary_10_1109_TNSM_2024_3405004 crossref_primary_10_1109_JIOT_2024_3520827 crossref_primary_10_1007_s12083_023_01531_8 crossref_primary_10_3390_s22020450 crossref_primary_10_1016_j_asoc_2024_111483 crossref_primary_10_1016_j_knosys_2022_108441 crossref_primary_10_1109_TPDS_2022_3202887 crossref_primary_10_1016_j_sysarc_2024_103279 crossref_primary_10_1007_s10462_024_11036_2 crossref_primary_10_1109_TIFS_2025_3550777 crossref_primary_10_1007_s10489_024_06046_0 crossref_primary_10_1007_s12652_023_04531_x crossref_primary_10_3389_fcomp_2025_1538277 crossref_primary_10_1109_COMST_2023_3316615 crossref_primary_10_38124_ijisrt_25jul392 crossref_primary_10_1016_j_neucom_2025_130844 crossref_primary_10_1016_j_iot_2025_101579 crossref_primary_10_1109_TMC_2023_3340338 crossref_primary_10_3390_educsci13060566 crossref_primary_10_1109_TMC_2021_3074816 crossref_primary_10_1109_ACCESS_2024_3431031 crossref_primary_10_1109_TGCN_2024_3417379 crossref_primary_10_1016_j_jpdc_2024_104918 crossref_primary_10_1109_COMST_2021_3090430 crossref_primary_10_1109_TKDE_2025_3528551 crossref_primary_10_1109_TITS_2023_3333749 crossref_primary_10_1109_TIFS_2025_3581042 crossref_primary_10_1016_j_jpdc_2024_104916 crossref_primary_10_1016_j_inffus_2025_103187 crossref_primary_10_3390_electronics13163157 crossref_primary_10_1016_j_procs_2021_07_041 crossref_primary_10_1109_TIFS_2022_3227435 crossref_primary_10_1007_s10586_022_03763_4 crossref_primary_10_1016_j_sysarc_2024_103067 crossref_primary_10_1016_j_cie_2023_109592 crossref_primary_10_1016_j_iot_2023_100956 crossref_primary_10_1016_j_comnet_2024_110822 crossref_primary_10_3390_electronics12204364 crossref_primary_10_1145_3616868 crossref_primary_10_1002_spy2_457 crossref_primary_10_1016_j_compeleceng_2025_110160 crossref_primary_10_1109_TIFS_2023_3322328 crossref_primary_10_1109_TMC_2025_3566421 crossref_primary_10_1109_TCE_2024_3367494 crossref_primary_10_1109_TIFS_2022_3228753 crossref_primary_10_1177_03611981231159118 crossref_primary_10_1016_j_chbah_2025_100137 crossref_primary_10_1109_TIFS_2024_3490861 crossref_primary_10_1287_ijoc_2024_0554 crossref_primary_10_1109_TCSS_2023_3304649 crossref_primary_10_1177_14727978251366544 crossref_primary_10_1186_s13677_024_00618_8 crossref_primary_10_1007_s12083_024_01759_y crossref_primary_10_1007_s11432_023_3918_9 crossref_primary_10_1007_s11633_022_1343_2 crossref_primary_10_1016_j_comnet_2024_110837 crossref_primary_10_3389_fdata_2024_1467222 crossref_primary_10_1016_j_patcog_2024_111143 crossref_primary_10_1016_j_jisa_2022_103201 crossref_primary_10_1016_j_future_2023_04_017 crossref_primary_10_1109_TII_2021_3098010 crossref_primary_10_1109_TDSC_2024_3350206 crossref_primary_10_1109_ACCESS_2022_3141709 crossref_primary_10_1016_j_pmcj_2024_101875 crossref_primary_10_1007_s12083_025_01952_7 crossref_primary_10_1109_TCE_2024_3525084 crossref_primary_10_3390_fi17010018 crossref_primary_10_1109_TBDATA_2023_3264109 crossref_primary_10_1109_TCAD_2024_3509793 crossref_primary_10_3390_app14031224 crossref_primary_10_1002_int_23056 crossref_primary_10_1109_TIFS_2023_3324726 crossref_primary_10_1109_JIOT_2024_3382875 crossref_primary_10_1109_JIOT_2024_3431294 crossref_primary_10_1109_TC_2023_3272801 crossref_primary_10_1109_TIFS_2023_3243490 crossref_primary_10_1109_ACCESS_2024_3424934 crossref_primary_10_1109_JIOT_2023_3313055 crossref_primary_10_1109_TMC_2025_3551368 crossref_primary_10_1007_s11432_024_4465_3 crossref_primary_10_1109_JIOT_2022_3165596 crossref_primary_10_1109_TWC_2022_3143543 crossref_primary_10_1109_JSAC_2023_3310103 crossref_primary_10_1109_TDSC_2022_3208630 crossref_primary_10_1007_s11042_023_17107_w crossref_primary_10_1109_JIOT_2025_3540103 crossref_primary_10_1109_TII_2021_3134257 crossref_primary_10_3390_electronics12183984 crossref_primary_10_1109_JIOT_2022_3151193 crossref_primary_10_1109_ACCESS_2023_3253026 crossref_primary_10_1109_TITS_2022_3179501 crossref_primary_10_1109_TII_2022_3173996 crossref_primary_10_1109_TSP_2023_3284376 crossref_primary_10_1109_TVT_2024_3380582 crossref_primary_10_1016_j_eswa_2025_128600 crossref_primary_10_1109_JIOT_2025_3587067 crossref_primary_10_1109_JIOT_2021_3086910 crossref_primary_10_1016_j_comcom_2024_04_024 crossref_primary_10_1109_JIOT_2024_3462674 crossref_primary_10_1109_JSEN_2022_3153338 crossref_primary_10_1007_s00607_024_01317_7 crossref_primary_10_1016_j_techsoc_2025_102910 crossref_primary_10_1016_j_bspc_2023_105893 crossref_primary_10_1016_j_jfranklin_2023_04_002 crossref_primary_10_1109_ACCESS_2021_3111118 crossref_primary_10_1109_TWC_2025_3555212 crossref_primary_10_1109_TIFS_2025_3540312 crossref_primary_10_1109_TIFS_2024_3453031 crossref_primary_10_1109_TIT_2025_3567215 crossref_primary_10_3389_frai_2021_746497 crossref_primary_10_1016_j_knosys_2023_110658 crossref_primary_10_1109_TII_2023_3333914 crossref_primary_10_1007_s10489_024_06211_5 crossref_primary_10_1109_JIOT_2021_3104833 crossref_primary_10_1109_TIFS_2025_3536612 crossref_primary_10_1016_j_neucom_2022_04_072 crossref_primary_10_1145_3695876 crossref_primary_10_1016_j_engappai_2021_104468 crossref_primary_10_1016_j_jnca_2023_103768 crossref_primary_10_1016_j_future_2024_01_009 crossref_primary_10_1109_ACCESS_2024_3363884 crossref_primary_10_1016_j_future_2023_03_010 crossref_primary_10_1109_JIOT_2023_3288886 crossref_primary_10_1016_j_future_2023_03_014 crossref_primary_10_14201_adcaij_31647 crossref_primary_10_1007_s11227_023_05846_4 crossref_primary_10_1109_ACCESS_2023_3280637 crossref_primary_10_1109_LSP_2024_3453200 crossref_primary_10_1109_LSP_2024_3400916 crossref_primary_10_1016_j_jnca_2025_104181 crossref_primary_10_1109_TMC_2024_3504271 crossref_primary_10_1016_j_cose_2024_103911 crossref_primary_10_1148_ryai_240485 crossref_primary_10_3389_fmed_2024_1409314 crossref_primary_10_1016_j_adhoc_2025_103761 crossref_primary_10_1016_j_adhoc_2025_103760 crossref_primary_10_1016_j_future_2024_107674 crossref_primary_10_1109_TII_2024_3423457 crossref_primary_10_1145_3708495 crossref_primary_10_1109_JIOT_2025_3584818 crossref_primary_10_1109_ACCESS_2024_3404948 crossref_primary_10_3390_s23156986 crossref_primary_10_1016_j_comnet_2025_111346 crossref_primary_10_1007_s11390_023_2972_9 crossref_primary_10_1016_j_compchemeng_2024_108749 crossref_primary_10_1109_JSAC_2021_3118354 crossref_primary_10_1016_j_future_2024_107646 crossref_primary_10_1016_j_scs_2021_103663 crossref_primary_10_32604_cmes_2023_030512 crossref_primary_10_3390_jeta3030023 crossref_primary_10_3390_math11214547 crossref_primary_10_1108_IJWIS_04_2022_0078 crossref_primary_10_14778_3718057_3718061 crossref_primary_10_1109_TIFS_2024_3374590 crossref_primary_10_1109_TIFS_2024_3379852 crossref_primary_10_1109_JSYST_2022_3218894 crossref_primary_10_1109_ACCESS_2021_3094089 crossref_primary_10_1002_spy2_70032 crossref_primary_10_1145_3596907 crossref_primary_10_1016_j_neucom_2022_11_011 crossref_primary_10_1109_ACCESS_2023_3246126 crossref_primary_10_1109_TII_2023_3331726 crossref_primary_10_1007_s10462_024_10796_1 crossref_primary_10_54097_bfp6m518 crossref_primary_10_1007_s10489_025_06533_y crossref_primary_10_1016_j_neucom_2023_126407 crossref_primary_10_1007_s11704_021_0598_z crossref_primary_10_1093_comjnl_bxaf037 crossref_primary_10_2196_56747 crossref_primary_10_1038_s41598_024_84797_z crossref_primary_10_1111_exsy_13283 crossref_primary_10_3390_s24030968 crossref_primary_10_3390_electronics13224478 crossref_primary_10_1109_TKDE_2024_3382002 crossref_primary_10_3390_fi14090246 crossref_primary_10_1007_s12559_024_10310_3 crossref_primary_10_1109_TKDE_2022_3230959 crossref_primary_10_3390_s20247030 crossref_primary_10_1016_j_future_2025_107706 crossref_primary_10_1109_JIOT_2024_3395310 crossref_primary_10_1186_s42400_024_00293_x crossref_primary_10_1007_s00354_022_00185_z crossref_primary_10_1109_JIOT_2023_3299736 crossref_primary_10_1016_j_cose_2024_103700 crossref_primary_10_1109_JIOT_2022_3194930 crossref_primary_10_1007_s10115_024_02285_2 crossref_primary_10_1016_j_eswa_2025_128667 crossref_primary_10_1109_JIOT_2023_3312118 crossref_primary_10_2478_amns_2023_2_00636 crossref_primary_10_1109_TCE_2024_3372696 crossref_primary_10_1109_TDSC_2024_3518841 crossref_primary_10_1109_TIFS_2022_3185770 crossref_primary_10_1145_3555374 crossref_primary_10_1007_s10479_024_06151_w crossref_primary_10_1145_3729385 crossref_primary_10_1109_TNSE_2024_3409755 crossref_primary_10_1016_j_comnet_2025_111130 crossref_primary_10_1007_s00146_025_02288_9 crossref_primary_10_1109_TIFS_2025_3598587 crossref_primary_10_1016_j_comnet_2025_111139 crossref_primary_10_1007_s11432_022_3678_7 crossref_primary_10_1109_COMST_2022_3175453 crossref_primary_10_1109_TII_2022_3203707 crossref_primary_10_32604_cmc_2024_055557 crossref_primary_10_3390_electronics12183938 crossref_primary_10_1007_s11042_024_18771_2 crossref_primary_10_1016_j_cose_2024_103715 crossref_primary_10_1016_j_future_2024_03_041 crossref_primary_10_1016_j_sigpro_2024_109742 crossref_primary_10_1109_TNNLS_2024_3383748 crossref_primary_10_1007_s13042_023_01956_w crossref_primary_10_1016_j_iot_2025_101532 crossref_primary_10_1016_j_segan_2023_101248 crossref_primary_10_1016_j_iot_2025_101530 crossref_primary_10_1109_LCOMM_2022_3180113 crossref_primary_10_1109_LSENS_2020_3046322 crossref_primary_10_1137_21M1465081 crossref_primary_10_1109_TIFS_2023_3273914 crossref_primary_10_1109_ACCESS_2024_3396146 crossref_primary_10_1109_TIFS_2023_3295949 crossref_primary_10_1109_JIOT_2022_3189361 crossref_primary_10_1002_cpe_8379 crossref_primary_10_3390_electronics12153295 crossref_primary_10_1038_s41467_022_33407_5 crossref_primary_10_1109_TSC_2024_3520867 crossref_primary_10_1145_3570953 crossref_primary_10_1016_j_neucom_2022_10_006 crossref_primary_10_1109_TWC_2023_3279442 crossref_primary_10_1109_JIOT_2024_3363712 crossref_primary_10_1186_s13040_024_00414_9 crossref_primary_10_1109_ACCESS_2024_3495702 crossref_primary_10_1109_TPDS_2025_3578522 crossref_primary_10_3390_network4020007 crossref_primary_10_1109_JIOT_2024_3407584 crossref_primary_10_1109_TCYB_2021_3139076 crossref_primary_10_1109_TVT_2024_3369942 crossref_primary_10_3390_math12162479 crossref_primary_10_1109_TITS_2023_3273167 crossref_primary_10_1587_transfun_2024DMP0010 crossref_primary_10_1109_JIOT_2021_3085429 crossref_primary_10_1145_3546872 crossref_primary_10_1109_JSAC_2020_3036948 crossref_primary_10_1016_j_ins_2023_119717 crossref_primary_10_1186_s12879_024_10230_5 crossref_primary_10_1007_s11227_025_07593_0 crossref_primary_10_1016_j_inffus_2023_101824 crossref_primary_10_1016_j_future_2022_08_004 crossref_primary_10_1109_JIOT_2021_3131258 crossref_primary_10_1109_TIFS_2022_3214717 crossref_primary_10_1016_j_jnca_2022_103486 crossref_primary_10_1007_s11227_023_05378_x crossref_primary_10_1109_TII_2023_3342897 crossref_primary_10_1109_TIFS_2022_3140687 crossref_primary_10_1109_IOTM_001_2300075 crossref_primary_10_3390_electronics13040671 crossref_primary_10_1109_ACCESS_2021_3124020 crossref_primary_10_1109_ACCESS_2022_3154826 crossref_primary_10_1109_TDSC_2021_3128679 crossref_primary_10_1109_TKDE_2025_3580796 crossref_primary_10_1007_s10462_023_10550_z crossref_primary_10_1109_TMC_2024_3443862 crossref_primary_10_1109_ACCESS_2023_3277858 crossref_primary_10_1145_3550289 crossref_primary_10_1109_ACCESS_2023_3310400 crossref_primary_10_1145_3544837 crossref_primary_10_1109_JIOT_2024_3409610 crossref_primary_10_1109_TNSE_2024_3352734 crossref_primary_10_3390_electronics12224633 crossref_primary_10_1148_ryai_240637 crossref_primary_10_1109_JIOT_2024_3396217 crossref_primary_10_1016_j_knosys_2024_111511 crossref_primary_10_1016_j_comnet_2021_108671 crossref_primary_10_1109_TSC_2022_3195179 crossref_primary_10_1109_TWC_2020_3038407 crossref_primary_10_3390_app14062345 crossref_primary_10_1016_j_hcc_2025_100302 crossref_primary_10_1109_TMC_2023_3332034 crossref_primary_10_1016_j_comnet_2021_108661 crossref_primary_10_1109_TIFS_2023_3258255 crossref_primary_10_1016_j_cels_2021_10_003 crossref_primary_10_1109_JIOT_2023_3347552 crossref_primary_10_1109_ACCESS_2024_3523909 crossref_primary_10_1109_TIFS_2025_3593938 crossref_primary_10_1109_JIOT_2021_3132363 crossref_primary_10_1109_TCSVT_2021_3105723 crossref_primary_10_1145_3633202 crossref_primary_10_1016_j_comnet_2024_110358 crossref_primary_10_1109_ACCESS_2025_3573933 crossref_primary_10_32604_cmes_2024_048932 crossref_primary_10_3390_electronics14163237 crossref_primary_10_1109_JIOT_2024_3417003 crossref_primary_10_1016_j_csi_2023_103827 crossref_primary_10_1145_3766066 crossref_primary_10_1016_j_eswa_2024_124724 crossref_primary_10_1109_ACCESS_2024_3520665 crossref_primary_10_3390_machines11060636 crossref_primary_10_1109_TII_2021_3105492 crossref_primary_10_1080_17517575_2022_2101025 crossref_primary_10_1109_TIFS_2023_3271268 crossref_primary_10_1109_TPDS_2022_3206480 crossref_primary_10_1109_TIFS_2024_3402993 crossref_primary_10_1038_s41746_024_01272_9 crossref_primary_10_1109_TPAMI_2023_3332428 crossref_primary_10_1016_j_knosys_2023_110347 crossref_primary_10_1109_TIFS_2024_3472531 crossref_primary_10_1016_j_csbj_2024_10_037 crossref_primary_10_1002_mp_16964 crossref_primary_10_1109_TNSM_2024_3525338 crossref_primary_10_1109_TKDE_2024_3430819 crossref_primary_10_1007_s00586_024_08172_2 crossref_primary_10_1016_j_adhoc_2023_103262 crossref_primary_10_1016_j_jisa_2021_102949 crossref_primary_10_1109_TCCN_2024_3519355 crossref_primary_10_1109_MCI_2024_3363971 crossref_primary_10_1007_s12652_022_04367_x crossref_primary_10_1016_j_csi_2025_104019 crossref_primary_10_1016_j_gfs_2021_100493 crossref_primary_10_1002_int_22993 crossref_primary_10_1016_j_jspi_2024_106186 crossref_primary_10_1109_TIFS_2025_3530676 crossref_primary_10_3390_electronics12040870 crossref_primary_10_1007_s11390_024_2635_5 crossref_primary_10_1109_TMC_2025_3533090 crossref_primary_10_1177_30504554251340238 crossref_primary_10_1109_LWC_2022_3181509 crossref_primary_10_1109_TIFS_2020_3043139 crossref_primary_10_1109_ACCESS_2024_3360691 crossref_primary_10_1109_TVT_2024_3524834 crossref_primary_10_1109_TIFS_2022_3196274 crossref_primary_10_1007_s00521_025_11420_1 crossref_primary_10_1016_j_future_2024_107637 crossref_primary_10_1109_ACCESS_2021_3118642 crossref_primary_10_1007_s10586_024_04845_1 crossref_primary_10_1109_TKDE_2024_3372708 crossref_primary_10_3390_electronics14010177 crossref_primary_10_1016_j_ipm_2022_103061 crossref_primary_10_1145_3656344 crossref_primary_10_1016_j_neucom_2024_127663 crossref_primary_10_1109_TC_2023_3239542 crossref_primary_10_1016_j_semradonc_2022_06_009 crossref_primary_10_3390_fi16100374 crossref_primary_10_3390_app12168239 crossref_primary_10_1145_3606017 crossref_primary_10_1007_s10994_023_06332_x crossref_primary_10_1109_ACCESS_2024_3448470 crossref_primary_10_3390_bdcc6040127 crossref_primary_10_1007_s00259_022_06053_8 crossref_primary_10_1109_TCSS_2023_3322824 crossref_primary_10_1016_j_cmpb_2023_107845 crossref_primary_10_3390_electronics13214187 crossref_primary_10_1109_ACCESS_2025_3576135 crossref_primary_10_1007_s11042_021_11751_w crossref_primary_10_1016_j_knosys_2024_111534 crossref_primary_10_1109_TMC_2024_3477616 crossref_primary_10_1109_TIFS_2024_3515797 crossref_primary_10_1002_int_22727 crossref_primary_10_1016_j_comnet_2025_111555 crossref_primary_10_1109_TIFS_2024_3515793 crossref_primary_10_1177_10692509241301588 crossref_primary_10_1109_TPDS_2021_3127712 crossref_primary_10_3390_electronics13122276 crossref_primary_10_1109_ACCESS_2025_3593953 crossref_primary_10_1007_s00607_024_01257_2 crossref_primary_10_3390_healthcare11152199 crossref_primary_10_1038_s41598_025_16158_3 crossref_primary_10_3390_app12105174 crossref_primary_10_1109_ACCESS_2025_3554138 crossref_primary_10_3390_jmse13010032 crossref_primary_10_1016_j_segan_2025_101784 crossref_primary_10_1109_JIOT_2023_3237806 crossref_primary_10_1109_TIFS_2024_3420135 crossref_primary_10_1109_ACCESS_2021_3074221 crossref_primary_10_1109_TPDS_2024_3354713 crossref_primary_10_1109_TPDS_2021_3138848 crossref_primary_10_3390_electronics12040842 crossref_primary_10_1109_TWC_2023_3245621 crossref_primary_10_1109_TBDATA_2025_3534622 crossref_primary_10_1109_TIFS_2025_3577498 crossref_primary_10_3390_sym14020195 crossref_primary_10_3390_electronics12102287 crossref_primary_10_1016_j_ejor_2023_12_013 crossref_primary_10_1109_TNSE_2022_3185327 crossref_primary_10_1109_TII_2022_3161517 crossref_primary_10_1109_TNSE_2025_3546777 crossref_primary_10_3390_math10244766 crossref_primary_10_1007_s10489_024_06209_z crossref_primary_10_1109_TBDATA_2022_3205705 crossref_primary_10_1016_j_imu_2024_101547 crossref_primary_10_1145_3560486 crossref_primary_10_1016_j_trc_2024_104743 crossref_primary_10_1145_3560485 crossref_primary_10_1109_TVT_2023_3287221 crossref_primary_10_3390_su132011459 crossref_primary_10_1109_TIFS_2023_3309095 crossref_primary_10_1016_j_neucom_2025_130579 crossref_primary_10_1109_TMC_2023_3268323 crossref_primary_10_1109_MNET_134_2200619 crossref_primary_10_1007_s10207_024_00813_3 crossref_primary_10_1016_j_knosys_2024_112208 crossref_primary_10_1109_JIOT_2023_3292232 crossref_primary_10_1109_TCE_2023_3320122 crossref_primary_10_1109_TNSM_2024_3399534 crossref_primary_10_1016_j_cmpb_2025_108870 crossref_primary_10_1109_TGCN_2024_3373886 crossref_primary_10_1109_JIOT_2024_3360094 crossref_primary_10_1016_j_sysconle_2025_106147 crossref_primary_10_1007_s11227_024_06845_9 crossref_primary_10_1016_j_neucom_2024_128317 crossref_primary_10_1016_j_im_2024_103922 crossref_primary_10_1016_j_comnet_2024_110510 crossref_primary_10_1063_5_0293257 crossref_primary_10_1109_TMC_2025_3553501 crossref_primary_10_1016_j_jisa_2025_104039 crossref_primary_10_1145_3501296 crossref_primary_10_1016_j_artmed_2024_103024 crossref_primary_10_1109_TAI_2024_3389611 crossref_primary_10_3390_aerospace12010041 crossref_primary_10_1109_TDSC_2024_3429503 crossref_primary_10_1109_TIFS_2025_3580231 crossref_primary_10_1016_j_dcan_2024_03_004 crossref_primary_10_1109_TDSC_2023_3321565 crossref_primary_10_1002_ett_4757 crossref_primary_10_1109_TCE_2024_3499959 crossref_primary_10_1109_ACCESS_2024_3458911 crossref_primary_10_3390_electronics12132951 crossref_primary_10_1109_TMC_2025_3531919 crossref_primary_10_1109_ACCESS_2024_3378126 crossref_primary_10_1109_ACCESS_2025_3560211 crossref_primary_10_3390_electronics14112263 crossref_primary_10_1109_TDSC_2023_3274119 crossref_primary_10_1109_JIOT_2022_3172114 crossref_primary_10_1109_JIOT_2023_3329363 crossref_primary_10_1016_j_future_2023_07_033 crossref_primary_10_1016_j_eswa_2025_129063 crossref_primary_10_1016_j_neunet_2025_107199 crossref_primary_10_1016_j_fmre_2024_01_011 crossref_primary_10_1016_j_cose_2025_104473 crossref_primary_10_1007_s10586_024_05061_7 crossref_primary_10_1016_j_compeleceng_2023_108986 crossref_primary_10_1109_TIFS_2024_3357288 crossref_primary_10_1007_s41666_023_00132_7 crossref_primary_10_1109_JIOT_2024_3405855 crossref_primary_10_1016_j_jpdc_2024_104976 crossref_primary_10_1109_TMC_2024_3398801 crossref_primary_10_3390_electronics14020361 crossref_primary_10_1016_j_comnet_2024_110321 crossref_primary_10_1016_j_sysarc_2025_103364 crossref_primary_10_32604_cmc_2023_039487 crossref_primary_10_1109_TMC_2025_3561791 crossref_primary_10_1016_j_comnet_2024_110560 crossref_primary_10_1145_3665220 crossref_primary_10_1016_j_inffus_2023_102029 crossref_primary_10_1016_j_rser_2023_114091 crossref_primary_10_1007_s10462_023_10563_8 crossref_primary_10_1016_j_sysarc_2022_102418 crossref_primary_10_3390_fi17060233 crossref_primary_10_3390_ani11102981 crossref_primary_10_1016_j_comcom_2025_108053 crossref_primary_10_1007_s10489_022_03435_1 crossref_primary_10_1016_j_future_2025_108140 crossref_primary_10_1109_TVCG_2022_3209347 crossref_primary_10_1016_j_comnet_2024_110798 crossref_primary_10_1016_j_comnet_2025_111705 crossref_primary_10_1016_j_iot_2023_100966 crossref_primary_10_1016_j_future_2023_06_010 crossref_primary_10_1109_JBHI_2023_3306425 crossref_primary_10_1109_TIM_2025_3568978 crossref_primary_10_1088_1742_6596_2138_1_012010 crossref_primary_10_1007_s11276_022_03109_3 crossref_primary_10_1109_JIOT_2022_3143842 crossref_primary_10_1109_JIOT_2024_3521609 crossref_primary_10_3390_app15031261 crossref_primary_10_1109_TETC_2024_3356068 crossref_primary_10_1186_s42400_021_00105_6 crossref_primary_10_1109_TII_2022_3145010 crossref_primary_10_1109_JIOT_2025_3576225 crossref_primary_10_1109_JETCAS_2023_3293253 crossref_primary_10_1109_ACCESS_2022_3208715 crossref_primary_10_3390_electronics13173423 crossref_primary_10_1109_TNSE_2021_3100096 crossref_primary_10_1016_j_dsp_2023_104353 crossref_primary_10_1109_COMST_2024_3430368 crossref_primary_10_1016_j_future_2023_05_002 crossref_primary_10_3390_s25072197 crossref_primary_10_1109_TAI_2024_3363670 crossref_primary_10_1007_s10489_024_05521_y crossref_primary_10_1007_s10489_024_05589_6 crossref_primary_10_1093_database_baaf016 crossref_primary_10_1109_JIOT_2023_3282899 |
| Cites_doi | 10.1109/ICASSP40776.2020.9053740 10.1109/TCOMM.2019.2944169 10.1109/JSAC.2019.2933890 10.1109/TPDS.2019.2899097 10.1109/TMC.2018.2853746 10.1145/1065167.1065184 10.1109/5.726791 10.1145/2976749.2978318 10.1109/INFOCOM.2019.8737464 10.1109/MNET.2019.1800286 10.1109/ICC.2019.8761267 10.1109/MNET.001.1800510 10.1145/2660267.2660348 10.1109/CDC.2012.6426626 10.1145/2810103.2813677 10.1561/0400000042 10.1109/INFOCOM.2019.8737416 10.1145/2810103.2813687 10.1109/ICDE.2019.00063 10.1109/JSAC.2019.2904348 10.1145/3298981 10.1109/JIOT.2019.2907245 10.1109/COMST.2018.2844341 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 KR7 L7M L~C L~D |
| DOI | 10.1109/TIFS.2020.2988575 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Civil Engineering Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1556-6021 |
| EndPage | 3469 |
| ExternalDocumentID | 10_1109_TIFS_2020_2988575 9069945 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Key Research and Development Program grantid: 2018YFB1004800 – fundername: Princeton Center for Statistics and Machine Learning under a Data X Grant – fundername: U.S. National Science Foundation grantid: CCF-1908308 funderid: 10.13039/100000001 – fundername: National Natural Science Foundation of China grantid: 61872184; 61727802 funderid: 10.13039/501100001809 – fundername: SUTD Growth Plan Grant for AI |
| GroupedDBID | 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 KR7 L7M L~C L~D |
| ID | FETCH-LOGICAL-c336t-cf659bda33ad50a89874eab747bb86acd1fa82b6f79fa3f3cb3db680a5e7f13f3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 1497 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000545212900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1556-6013 |
| IngestDate | Mon Jun 30 04:49:36 EDT 2025 Sat Nov 29 03:49:40 EST 2025 Tue Nov 18 22:37:10 EST 2025 Wed Aug 27 02:14:03 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c336t-cf659bda33ad50a89874eab747bb86acd1fa82b6f79fa3f3cb3db680a5e7f13f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | http://hdl.handle.net/11343/251362 |
| PQID | 2414533724 |
| PQPubID | 85506 |
| PageCount | 16 |
| ParticipantIDs | crossref_citationtrail_10_1109_TIFS_2020_2988575 crossref_primary_10_1109_TIFS_2020_2988575 ieee_primary_9069945 proquest_journals_2414533724 |
| PublicationCentury | 2000 |
| PublicationDate | 20200000 2020-00-00 20200101 |
| PublicationDateYYYYMMDD | 2020-01-01 |
| PublicationDate_xml | – year: 2020 text: 20200000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on information forensics and security |
| PublicationTitleAbbrev | TIFS |
| PublicationYear | 2020 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 xiangru (ref17) 2015 ref12 ref37 ref15 ref36 ref14 ref10 brendan mcmahan (ref6) 2016 ref2 ref1 ref16 mohammad (ref8) 2019 ref24 ma (ref23) 2019 ref26 ref25 ref20 ref22 ref21 nesterov (ref38) 2014 brendan mcmahan (ref32) 2017 wu (ref30) 2019 ref28 ref27 lian (ref18) 2017 ref29 ref9 ref4 ref3 li (ref31) 2019 kone?ný (ref7) 2016 li (ref11) 2019 ref5 geyer (ref34) 2017 ryffel (ref33) 2018 li (ref19) 2018 truex (ref35) 2018 |
| References_xml | – ident: ref15 doi: 10.1109/ICASSP40776.2020.9053740 – year: 2019 ident: ref11 article-title: Federated learning: Challenges, methods, and future directions publication-title: arXiv 1908 07873 – ident: ref13 doi: 10.1109/TCOMM.2019.2944169 – ident: ref3 doi: 10.1109/JSAC.2019.2933890 – year: 2019 ident: ref31 article-title: Differentially private meta-learning publication-title: arXiv 1909 05830 – ident: ref28 doi: 10.1109/TPDS.2019.2899097 – ident: ref1 doi: 10.1109/TMC.2018.2853746 – year: 2017 ident: ref32 article-title: Learning differentially private recurrent language models publication-title: arXiv 1710 06963 – ident: ref25 doi: 10.1145/1065167.1065184 – start-page: 5336 year: 2017 ident: ref18 article-title: Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent publication-title: Proc ACM NIPS – ident: ref37 doi: 10.1109/5.726791 – ident: ref29 doi: 10.1145/2976749.2978318 – year: 2019 ident: ref23 article-title: On safeguarding privacy and security in the framework of federated learning publication-title: arXiv 1909 06512 – ident: ref12 doi: 10.1109/INFOCOM.2019.8737464 – ident: ref9 doi: 10.1109/MNET.2019.1800286 – year: 2016 ident: ref6 article-title: Communication-efficient learning of deep networks from decentralized data publication-title: arXiv 1602 05629 – ident: ref14 doi: 10.1109/ICC.2019.8761267 – ident: ref4 doi: 10.1109/MNET.001.1800510 – ident: ref26 doi: 10.1145/2660267.2660348 – start-page: 2737 year: 2015 ident: ref17 article-title: Asynchronous parallel stochastic gradient for nonconvex optimization publication-title: Proc ACM NIPS – year: 2019 ident: ref8 article-title: Adaptive task allocation for asynchronous federated mobile edge learning publication-title: arXiv 1905 01656 – ident: ref16 doi: 10.1109/CDC.2012.6426626 – ident: ref36 doi: 10.1145/2810103.2813677 – year: 2014 ident: ref38 publication-title: Introductory Lectures on Convex Optimization A Basic Course – year: 2018 ident: ref19 article-title: Federated optimization in heterogeneous networks publication-title: arXiv 1812 06127 – year: 2017 ident: ref34 article-title: Differentially private federated learning: A client level perspective publication-title: arXiv 1712 07557 – year: 2018 ident: ref35 article-title: A hybrid approach to privacy-preserving federated learning publication-title: arXiv 1812 03224 – ident: ref24 doi: 10.1561/0400000042 – year: 2018 ident: ref33 article-title: A generic framework for privacy preserving deep learning publication-title: arXiv 1811 04017 – ident: ref22 doi: 10.1109/INFOCOM.2019.8737416 – ident: ref21 doi: 10.1145/2810103.2813687 – year: 2019 ident: ref30 article-title: The value of collaboration in convex machine learning with differential privacy publication-title: arXiv 1906 09679 – year: 2016 ident: ref7 article-title: Federated learning: Strategies for improving communication efficiency publication-title: arXiv 1610 05492 – ident: ref27 doi: 10.1109/ICDE.2019.00063 – ident: ref20 doi: 10.1109/JSAC.2019.2904348 – ident: ref10 doi: 10.1145/3298981 – ident: ref2 doi: 10.1109/JIOT.2019.2907245 – ident: ref5 doi: 10.1109/COMST.2018.2844341 |
| SSID | ssj0044168 |
| Score | 2.7173688 |
| Snippet | Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients' private data from being exposed to... Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 3454 |
| SubjectTerms | Agglomeration Algorithms Analytical models Artificial neural networks client selection Clients Computer simulation Convergence convergence performance differential privacy Distributed databases Federated learning information leakage Levels Machine learning Mathematical models Parameters Privacy Scheduling Servers Tradeoffs Training |
| Title | Federated Learning With Differential Privacy: Algorithms and Performance Analysis |
| URI | https://ieeexplore.ieee.org/document/9069945 https://www.proquest.com/docview/2414533724 |
| Volume | 15 |
| WOSCitedRecordID | wos000545212900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1556-6021 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0044168 issn: 1556-6013 databaseCode: RIE dateStart: 20060101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UPOjBt7i-yMGTWE2bJmm8ibroRVZU9Fby1IV1V3ZXwX9v0qarogjeSpsppV8nM5N0vg9gTzijNRMksQU2SW6FSZTIScIJ1VxiGVL8SmyCX10VDw-iMwUHk14Ya23185k9DIfVXr4Z6NewVHYkMBMip9MwzTmre7WaWddH9brtjVKW-CKDxB3MFIuj28v2ja8EM3yYiSIoUn6LQZWoyo-ZuAov7cX_PdgSLMQ0Ep3UuC_DlO2vwGIj0YCix67A_Be-wVW4bgfqCJ9dGhR5VR_RfXf8hM6iTIp39x7qDLtvUr8fo5Pe42DoLz-PkOwb1PnsMUANl8ka3LXPb08vkqipkGhC2DjRjlGhjCREGhqgKHhupfJFhVIFk9qkThaZYo4LJ4kjWhGjWIEltdyl_sQ6zPQHfbsBiFqChXRUEmzyzBLprLM8TVUqpPCGLcDNWy51JBwPuhe9sio8sCgDMGUApozAtGB_YvJSs238NXg1IDEZGEFowXYDZRn9cVT6PCX3iS3P8s3frbZgLty7XlzZhpnx8NXuwKx-G3dHw93qU_sANRfSng |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED6NgsT2sELLtLIBfuAJkdWJ7STmrQKqVoyqiCL6FvlnqdS1U39J--9nJ04BgZB4ixKfEuXL-e7s3PcBvOZWK5VyEpkc64gariPJKYkywlQmsPApfik2kY1G-XTKx0fw9tALY4wpfz4zV_6w3MvXK7XzS2VdjlPOKXsADxmlCa66tep518X1qvGNsTRyZQYJe5gx5t3JsP_V1YIJvkp47jUpf4tCpazKH3NxGWD6zf97tCdwGhJJ1KuQfwpHZtmCZi3SgILPtuDkF8bBNnzpe_IIl19qFJhVZ-j7fPsDfQhCKc7hF2i8nu-FunuHeovZau0u32yQWGo0_tllgGo2k2fwrf9x8n4QBVWFSBGSbiNlU8alFoQIzTwYeUaNkK6skDJPhdKxFXkiU5txK4glShIt0xwLZjIbuxNn0FiuluYcEDMEc2GZIFjTxBBhjTVZHMuYC-4MO4Drt1yoQDnulS8WRVl6YF54YAoPTBGA6cCbg8ltxbfxr8Ftj8RhYAChA5c1lEXwyE3hMhXqUtssoc__bvUKHg8mn6-L6-Ho0wUc-_tUSy2X0Niud-YFPFL77Xyzfll-dvdQ69Xl |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Federated+Learning+With+Differential+Privacy%3A+Algorithms+and+Performance+Analysis&rft.jtitle=IEEE+transactions+on+information+forensics+and+security&rft.au=Wei%2C+Kang&rft.au=Li%2C+Jun&rft.au=Ding%2C+Ming&rft.au=Ma%2C+Chuan&rft.date=2020&rft.pub=IEEE&rft.issn=1556-6013&rft.volume=15&rft.spage=3454&rft.epage=3469&rft_id=info:doi/10.1109%2FTIFS.2020.2988575&rft.externalDocID=9069945 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1556-6013&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1556-6013&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1556-6013&client=summon |