Understanding adversarial attacks on deep learning based medical image analysis systems
•Medical image DNNs are easier to be attacked than natural non-medical image DNNs.•Complex biological textures of medical images may lead to more vulnerable regions.•State-of-the-art deep networks can be overparameterized for medical imaging tasks.•Medical image adversarial attacks can also be easil...
Uložené v:
| Vydané v: | Pattern recognition Ročník 110; s. 107332 |
|---|---|
| Hlavní autori: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Ltd
01.02.2021
|
| Predmet: | |
| ISSN: | 0031-3203, 1873-5142 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | •Medical image DNNs are easier to be attacked than natural non-medical image DNNs.•Complex biological textures of medical images may lead to more vulnerable regions.•State-of-the-art deep networks can be overparameterized for medical imaging tasks.•Medical image adversarial attacks can also be easily detected.•High detectability may be caused by perturbations outside the pathological regions.
Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks with small imperceptible perturbations. This raises safety concerns about the deployment of these systems in clinical settings. In this paper, we provide a deeper understanding of adversarial examples in the context of medical images. We find that medical DNN models can be more vulnerable to adversarial attacks compared to models for natural images, according to two different viewpoints. Surprisingly, we also find that medical adversarial attacks can be easily detected, i.e., simple detectors can achieve over 98% detection AUC against state-of-the-art attacks, due to fundamental feature differences compared to normal examples. We believe these findings may be a useful basis to approach the design of more explainable and secure medical deep learning systems. |
|---|---|
| AbstractList | •Medical image DNNs are easier to be attacked than natural non-medical image DNNs.•Complex biological textures of medical images may lead to more vulnerable regions.•State-of-the-art deep networks can be overparameterized for medical imaging tasks.•Medical image adversarial attacks can also be easily detected.•High detectability may be caused by perturbations outside the pathological regions.
Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks with small imperceptible perturbations. This raises safety concerns about the deployment of these systems in clinical settings. In this paper, we provide a deeper understanding of adversarial examples in the context of medical images. We find that medical DNN models can be more vulnerable to adversarial attacks compared to models for natural images, according to two different viewpoints. Surprisingly, we also find that medical adversarial attacks can be easily detected, i.e., simple detectors can achieve over 98% detection AUC against state-of-the-art attacks, due to fundamental feature differences compared to normal examples. We believe these findings may be a useful basis to approach the design of more explainable and secure medical deep learning systems. |
| ArticleNumber | 107332 |
| Author | Gu, Lin Bailey, James Ma, Xingjun Wang, Yisen Zhao, Yitian Niu, Yuhao Lu, Feng |
| Author_xml | – sequence: 1 givenname: Xingjun orcidid: 0000-0003-2099-4973 surname: Ma fullname: Ma, Xingjun email: xingjun.ma@unimelb.edu.au organization: School of Computing and Information Systems, The University of Melbourne, Parkville, VIC 3010, Australia – sequence: 2 givenname: Yuhao orcidid: 0000-0003-0423-0682 surname: Niu fullname: Niu, Yuhao email: niuyuhao@buaa.edu.cn organization: State Key Laboratory of VR Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China – sequence: 3 givenname: Lin surname: Gu fullname: Gu, Lin email: ling@nii.ac.jp organization: National Institute of Informatics, Tokyo 101-8430, Japan – sequence: 4 givenname: Yisen surname: Wang fullname: Wang, Yisen email: eewangyisen@gmail.com organization: Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 5 givenname: Yitian orcidid: 0000-0003-4357-4592 surname: Zhao fullname: Zhao, Yitian email: yitian.zhao@nimte.ac.cn organization: Cixi Instuitue of Biomedical Engineering, Ningbo Institute of Industrial Technology, Chinese Academy of Sciences, Ningbo, China – sequence: 6 givenname: James surname: Bailey fullname: Bailey, James email: baileyj@unimelb.edu.au organization: School of Computing and Information Systems, The University of Melbourne, Parkville, VIC 3010, Australia – sequence: 7 givenname: Feng orcidid: 0000-0001-9064-7964 surname: Lu fullname: Lu, Feng email: lufeng@buaa.edu.cn organization: State Key Laboratory of VR Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China |
| BookMark | eNqFkM1qwzAQhEVJoUnaN-hBL-BU0tpx3EOhhP5BoJeGHsVaWgeljhwkEcjb18Y99dCelt2dGZhvxia-88TYrRQLKeTybr84YjLdbqGEGk4lgLpgU7kqIStkriZsKgTIDJSAKzaLcS-ELPvHlH1uvaUQE3rr_I6jPfUbBoctx5TQfEXeeW6JjrwlDH4Q1RjJ8gNZZ3qZO-COOHpsz9FFHs8x0SFes8sG20g3P3POts9PH-vXbPP-8rZ-3GQGCpWyugSzApArrEgWhKIxkEMlyqVQCEi2BpRWNiJXdVNXta0NNFjlZK2wy7yBObsfc03oYgzUaOMSJtf5FNC1Wgo9INJ7PSLSAyI9IurN-S_zMfR1wvk_28Noo77YyVHQ0TjypgcSyCRtO_d3wDc-t4b6 |
| CitedBy_id | crossref_primary_10_1126_scirobotics_adt0187 crossref_primary_10_1016_j_neunet_2025_107341 crossref_primary_10_3348_jksr_2022_0156 crossref_primary_10_1007_s10489_023_05037_x crossref_primary_10_1016_j_cogsys_2023_101188 crossref_primary_10_1038_s42256_020_0186_1 crossref_primary_10_1016_j_neucom_2024_127726 crossref_primary_10_1109_MCE_2024_3443543 crossref_primary_10_1016_j_ejrad_2023_110786 crossref_primary_10_1016_j_heliyon_2022_e11209 crossref_primary_10_1016_j_irbm_2022_100748 crossref_primary_10_1016_j_cpet_2021_06_006 crossref_primary_10_1109_ACCESS_2025_3570898 crossref_primary_10_1016_j_imavis_2024_105272 crossref_primary_10_3390_diagnostics13142345 crossref_primary_10_1007_s43681_023_00368_4 crossref_primary_10_1109_ACCESS_2022_3216291 crossref_primary_10_3390_s22186905 crossref_primary_10_1109_JBHI_2021_3139541 crossref_primary_10_1155_2021_5363750 crossref_primary_10_3390_jimaging8060155 crossref_primary_10_1007_s11517_024_03226_5 crossref_primary_10_1038_s41467_021_27577_x crossref_primary_10_1088_1361_6560_ad3cb3 crossref_primary_10_1016_j_media_2021_102141 crossref_primary_10_1186_s12911_022_01891_w crossref_primary_10_1016_j_future_2022_03_008 crossref_primary_10_1111_risa_14666 crossref_primary_10_1016_j_patcog_2024_110632 crossref_primary_10_3390_jcm12093266 crossref_primary_10_1371_journal_pone_0307363 crossref_primary_10_3389_fnins_2023_1273931 crossref_primary_10_32604_cmes_2023_044169 crossref_primary_10_1145_3544014 crossref_primary_10_1007_s00500_021_06148_8 crossref_primary_10_3390_diagnostics15020230 crossref_primary_10_4274_balkanmedj_galenos_2022_2022_11_51 crossref_primary_10_1016_j_eswa_2025_128815 crossref_primary_10_1002_rob_22586 crossref_primary_10_1016_j_eswa_2025_126632 crossref_primary_10_1038_s41598_025_00890_x crossref_primary_10_3390_jimaging10080176 crossref_primary_10_1145_3711713 crossref_primary_10_3390_jimaging8020038 crossref_primary_10_1007_s00259_020_04879_8 crossref_primary_10_3390_electronics12051092 crossref_primary_10_1016_j_media_2024_103157 crossref_primary_10_1038_s41598_025_02294_3 crossref_primary_10_1016_j_compbiomed_2024_108585 crossref_primary_10_1109_ACCESS_2020_3042839 crossref_primary_10_1109_ACCESS_2021_3110473 crossref_primary_10_3390_bioengineering10121383 crossref_primary_10_1016_j_smhl_2024_100500 crossref_primary_10_1016_j_ejrad_2023_111156 crossref_primary_10_17816_socm619132 crossref_primary_10_1002_mp_15936 crossref_primary_10_1016_j_compbiomed_2024_107938 crossref_primary_10_1145_3594869 crossref_primary_10_1088_1361_6560_ad9e69 crossref_primary_10_1109_TFUZZ_2024_3473768 crossref_primary_10_1109_ACCESS_2024_3364818 crossref_primary_10_1016_j_matpr_2021_06_233 crossref_primary_10_32604_cmc_2022_030432 crossref_primary_10_1109_TMI_2022_3156268 crossref_primary_10_1016_j_patcog_2025_111652 crossref_primary_10_4103_ATMR_ATMR_55_25 crossref_primary_10_1109_TCYB_2022_3209175 crossref_primary_10_1002_wsbm_1548 crossref_primary_10_1016_j_patcog_2022_108824 crossref_primary_10_1007_s10489_021_03145_0 crossref_primary_10_1109_TEVC_2022_3151373 crossref_primary_10_1109_ACCESS_2020_3034766 crossref_primary_10_1038_s41467_022_33266_0 crossref_primary_10_3389_fdata_2023_1120989 crossref_primary_10_1016_j_inffus_2024_102716 crossref_primary_10_1109_TIP_2022_3211736 crossref_primary_10_1097_ICU_0000000000000846 crossref_primary_10_1007_s11063_025_11756_8 crossref_primary_10_1136_jme_2024_109905 crossref_primary_10_1145_3702638 crossref_primary_10_3390_bioengineering12090914 crossref_primary_10_3390_healthcare13080892 crossref_primary_10_1016_j_jobe_2021_102690 crossref_primary_10_1109_JBHI_2021_3110593 crossref_primary_10_1109_TIT_2023_3303221 crossref_primary_10_1016_j_jisa_2023_103621 crossref_primary_10_1109_JBHI_2021_3139575 crossref_primary_10_3390_cancers15041013 crossref_primary_10_1016_j_patcog_2022_108831 crossref_primary_10_1007_s11390_024_3515_8 crossref_primary_10_3390_s21062140 crossref_primary_10_1016_j_patcog_2024_110394 crossref_primary_10_1016_j_ins_2024_120705 crossref_primary_10_1016_j_heliyon_2024_e35683 crossref_primary_10_1016_j_media_2023_102802 crossref_primary_10_1007_s11517_022_02535_x crossref_primary_10_1007_s11517_025_03331_z crossref_primary_10_1109_ACCESS_2023_3250661 crossref_primary_10_1007_s00521_024_10516_4 crossref_primary_10_1016_j_adhoc_2025_103935 crossref_primary_10_1016_j_comcom_2025_108113 crossref_primary_10_1007_s12083_024_01751_6 crossref_primary_10_1016_j_imavis_2024_105405 crossref_primary_10_1016_j_compbiomed_2023_107310 crossref_primary_10_1007_s41870_023_01538_7 crossref_primary_10_58496_ADSA_2024_011 crossref_primary_10_1016_j_media_2025_103494 crossref_primary_10_3390_biomedicines10102545 crossref_primary_10_1109_ACCESS_2024_3396566 crossref_primary_10_1007_s11063_025_11730_4 crossref_primary_10_1177_03611981241302335 crossref_primary_10_1007_s10140_024_02306_1 crossref_primary_10_1145_3706061 crossref_primary_10_1016_j_compeleceng_2022_107691 crossref_primary_10_2196_24012 crossref_primary_10_1007_s11042_023_15575_8 crossref_primary_10_1007_s13042_025_02702_0 crossref_primary_10_7717_peerj_cs_2882 crossref_primary_10_1109_TAI_2024_3394798 crossref_primary_10_1007_s00530_023_01193_9 crossref_primary_10_1016_j_chb_2024_108222 crossref_primary_10_3390_rs16142570 crossref_primary_10_1111_exsy_12737 crossref_primary_10_3389_fmed_2025_1606238 crossref_primary_10_3390_s21155236 crossref_primary_10_1007_s10278_023_00916_8 crossref_primary_10_1016_j_patcog_2022_109037 crossref_primary_10_1088_1402_4896_ad3698 crossref_primary_10_1016_j_bspc_2024_106069 crossref_primary_10_1109_TII_2024_3423457 crossref_primary_10_1145_3593042 crossref_primary_10_1002_mp_15208 crossref_primary_10_1007_s00521_023_08737_0 crossref_primary_10_1016_j_imavis_2025_105601 crossref_primary_10_1117_1_JEI_31_6_063046 crossref_primary_10_1145_3627817 crossref_primary_10_1007_s10994_023_06314_z crossref_primary_10_1007_s11517_024_03098_9 crossref_primary_10_1016_j_patcog_2025_111401 crossref_primary_10_1016_j_artmed_2024_103024 crossref_primary_10_1051_epjconf_202430217005 crossref_primary_10_1016_j_eswa_2025_127319 crossref_primary_10_3390_cancers15174228 crossref_primary_10_1016_j_compbiomed_2024_108847 crossref_primary_10_1007_s11517_024_03026_x crossref_primary_10_1007_s11042_023_14702_9 crossref_primary_10_1108_IJWIS_04_2022_0080 crossref_primary_10_1016_j_neucom_2025_129577 crossref_primary_10_1186_s42400_024_00330_9 crossref_primary_10_1038_s41598_025_14408_y crossref_primary_10_3390_cancers15051548 crossref_primary_10_1109_ACCESS_2023_3266586 crossref_primary_10_32604_cmc_2023_034435 crossref_primary_10_1016_j_patcog_2021_108102 crossref_primary_10_1007_s40747_025_02038_w crossref_primary_10_1016_j_engappai_2024_108436 crossref_primary_10_1038_s41598_025_03546_y crossref_primary_10_1007_s13042_025_02568_2 crossref_primary_10_1016_j_patcog_2025_111638 crossref_primary_10_1016_j_apenergy_2024_122872 crossref_primary_10_3390_app13148295 crossref_primary_10_1145_3604937 crossref_primary_10_1109_TASLP_2023_3304476 crossref_primary_10_1166_jmihi_2021_3850 crossref_primary_10_1016_j_jisa_2025_104172 crossref_primary_10_3390_app15147856 crossref_primary_10_3103_S0146411622080211 crossref_primary_10_1007_s13534_024_00399_8 crossref_primary_10_1002_ett_4884 crossref_primary_10_1109_ACCESS_2021_3115764 crossref_primary_10_1016_j_artmed_2024_102830 crossref_primary_10_1002_widm_1567 crossref_primary_10_1016_j_rineng_2025_104327 crossref_primary_10_1109_TMI_2023_3335098 crossref_primary_10_1016_j_rxeng_2023_11_011 crossref_primary_10_3389_fmed_2025_1580583 crossref_primary_10_1016_j_compbiomed_2023_107248 crossref_primary_10_1007_s11227_022_04502_7 crossref_primary_10_1109_TIFS_2024_3352837 crossref_primary_10_1049_cit2_12155 crossref_primary_10_1186_s13635_024_00158_3 crossref_primary_10_1109_ACCESS_2023_3305368 crossref_primary_10_1016_j_neuroimage_2023_120289 crossref_primary_10_1007_s12530_024_09598_1 crossref_primary_10_1016_j_amjmed_2021_11_010 crossref_primary_10_1007_s43995_024_00060_6 crossref_primary_10_1145_3607190 crossref_primary_10_1259_bjr_20210527 crossref_primary_10_1016_j_eswa_2022_118698 crossref_primary_10_1016_j_patcog_2021_108249 crossref_primary_10_1016_j_compbiomed_2022_106422 crossref_primary_10_1007_s11227_022_04611_3 crossref_primary_10_1016_j_neucom_2024_128111 crossref_primary_10_1109_JIOT_2020_3013710 crossref_primary_10_1016_j_compbiomed_2023_107251 crossref_primary_10_1016_j_neucom_2025_129660 crossref_primary_10_1016_j_bspc_2025_108333 crossref_primary_10_1109_JIOT_2024_3514194 crossref_primary_10_1109_JAS_2023_123123 crossref_primary_10_3390_diagnostics12112708 crossref_primary_10_4018_IJSWIS_360651 crossref_primary_10_1109_ACCESS_2023_3299862 crossref_primary_10_1016_j_ejmp_2022_06_003 crossref_primary_10_1007_s13198_024_02482_w crossref_primary_10_1109_TIM_2024_3440388 crossref_primary_10_1016_j_iot_2024_101206 crossref_primary_10_1016_j_patcog_2024_110564 crossref_primary_10_1007_s11263_024_02233_1 crossref_primary_10_1089_ten_teb_2024_0216 crossref_primary_10_1016_j_cobme_2024_100561 crossref_primary_10_1007_s10462_023_10415_5 crossref_primary_10_1109_JBHI_2023_3348130 crossref_primary_10_1016_j_compbiomed_2023_106626 crossref_primary_10_1016_j_neunet_2024_107019 crossref_primary_10_1007_s00521_023_08921_2 crossref_primary_10_3390_math11204272 crossref_primary_10_1007_s11548_021_02505_y crossref_primary_10_3390_electronics10172132 crossref_primary_10_1038_s41598_025_97675_z crossref_primary_10_1016_j_diii_2025_05_006 crossref_primary_10_1016_j_eswa_2022_116815 crossref_primary_10_3390_app14030989 crossref_primary_10_1016_j_artmed_2022_102332 crossref_primary_10_1038_s41523_023_00577_4 crossref_primary_10_3390_computers13080203 |
| Cites_doi | 10.1038/nature21056 10.1016/j.patcog.2019.107040 10.1109/TMI.2014.2377694 10.1109/LGRS.2018.2872355 10.1109/TPAMI.2017.2655525 10.1016/S1359-6446(04)03334-3 10.1016/j.media.2019.04.005 10.1001/jama.2016.17216 10.1126/science.aaw4399 10.1016/j.patcog.2017.03.020 |
| ContentType | Journal Article |
| Copyright | 2020 |
| Copyright_xml | – notice: 2020 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.patcog.2020.107332 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-5142 |
| ExternalDocumentID | 10_1016_j_patcog_2020_107332 S0031320320301357 |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ABYKQ ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c352t-b73c83318a9e15ea0fc343907602a3aedb3a1d1f042bfb9bdbc3fa94edd0d64f3 |
| ISICitedReferencesCount | 329 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000585304300008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0031-3203 |
| IngestDate | Sat Nov 29 07:26:19 EST 2025 Tue Nov 18 22:19:41 EST 2025 Fri Feb 23 02:46:15 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Adversarial attack Adversarial example detection Medical image analysis |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c352t-b73c83318a9e15ea0fc343907602a3aedb3a1d1f042bfb9bdbc3fa94edd0d64f3 |
| ORCID | 0000-0003-4357-4592 0000-0001-9064-7964 0000-0003-2099-4973 0000-0003-0423-0682 |
| OpenAccessLink | https://doi.org/10.1016/j.patcog.2020.107332 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_patcog_2020_107332 crossref_primary_10_1016_j_patcog_2020_107332 elsevier_sciencedirect_doi_10_1016_j_patcog_2020_107332 |
| PublicationCentury | 2000 |
| PublicationDate | February 2021 2021-02-00 |
| PublicationDateYYYYMMDD | 2021-02-01 |
| PublicationDate_xml | – month: 02 year: 2021 text: February 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2021 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Goodfellow, Shlens, Szegedy (bib0009) 2015 Lu, Chen, Sato, Sato (bib0004) 2018; 40 He, Zhang, Ren, Sun (bib0001) 2016 Esteva, Kuprel, Novoa, Ko, Swetter, Blau, Thrun (bib0005) 2017; 542 Gu, Cheng (bib0019) 2015 Metzen, Genewein, Fischer, Bischoff (bib0036) 2017 Cheng, Zhang, Zhang (bib0022) 2015 Wu, Wang, Xia, Bailey, Ma (bib0029) 2020 Niu, Gu, Lu, Lv, Wang, Sato, Zhang, Xiao, Dai, Cheng (bib0017) 2019; vol. 33 Wang, Zhou, Shen, Park, Fishman, Yuille (bib0021) 2019 Ciresan, Giusti, Gambardella, Schmidhuber (bib0026) 2013; vol. 8150 Gulshan, Peng, Coram, Stumpe, Wu, Narayanaswamy, Venugopalan, et al. (bib0025) 2016 Liu, Liu, Fan, Ma, Zhang, Xie, Tao (bib0046) 2019; vol. 33 Menze, Jakab, Bauer, et al. (bib0024) 2015; 34 Zhou, Bai, Liu, Zhou, Hancock (bib0035) 2020; 98 . Jiang, Ma, Chen, Bailey, Jiang (bib0028) 2019 (2019). C. Zhang, A. Liu, X. Liu, Y. Xu, H. Yu, Y. Ma, T. Li, Interpreting and improving adversarial robustness with neuron sensitivity, arXiv Wang, Bai, Wang, Zhou, Ren (bib0002) 2019; 16 (2017). Cheng, Lu, Zhang (bib0011) 2018 Eykholt, Evtimov, Fernandes, Li, Rahmati, Xiao, Prakash, Kohno, Song (bib0010) 2018 Kurakin, Goodfellow, Bengio (bib0030) 2017 Roth, Lu, Farag, Shin, Liu, Turkbey, Summers (bib0007) 2015 Finlayson, Bowers, Ito, Zittrain, Beam, Kohane (bib0012) 2019; 363 Feinman, Curtin, Shintre, Gardner (bib0037) 2017 Kaggle, Kaggle diabetic retinopathy detection challenge, 2015 Bai, Yan, Yang, Bai, Zhou, Hancock (bib0003) 2018; 75 Paschali, Conjeti, Navarro, Navab (bib0016) 2018 F. Tramèr, N. Papernot, I. Goodfellow, D. Boneh, P. McDaniel, The space of transferable adversarial examples, arXiv Liu, Liu, Cai, Pujol, Kikinis, Feng (bib0023) 2014 Li, Zhu, Zhou, Xia, Shen, Fishman, Yuille (bib0015) 2019 Szegedy, Zaremba, Sutskever, Bruna, Erhan, Goodfellow, Fergus (bib0008) 2014 Simonyan, Vedaldi, Zisserman (bib0041) 2014 Wang, Zou, Yi, Bailey, Ma, Gu (bib0048) 2020 Pien, Fischman, Thrall, Sorensen (bib0018) 2005; 10 ISIC, The international skin imaging collaboration, 2019 Selvaraju, Cogswell, Das, Vedantam, Parikh, Batra (bib0045) 2017 Wang, Peng, Lu, Lu, Bagheri, Summers (bib0013) 2017 H. Yu, A. Liu, X. Liu, J. Yang, C. Zhang, Towards noise-robust neural networks via progressive adversarial training, arXiv Carlini, Wagner (bib0031) 2017 Ross, Doshi-Velez (bib0033) 2018 Lu, Issaranon, Forsyth (bib0043) 2017 Athalye, Carlini, Wagner (bib0034) 2018 Ma, Li, Wang, Erfani, Wijewickrema, Schoenebeck, Houle, Song, Bailey (bib0038) 2018 Bai, Feng, Wang, Dai, Xia, Jiang (bib0032) 2019 Liu, Gu, Lu (bib0020) 2019 Madry, Makelov, Schmidt, Tsipras, Vladu (bib0027) 2018 Shafahi, Najibi, Ghiasi, Xu, Dickerson, Studer, Davis, Taylor, Goldstein (bib0040) 2019 Wang, Ma, Bailey, Yi, Zhou, Gu (bib0047) 2019 Maaten, Hinton (bib0044) 2008; 9 Gulshan, Peng, Coram, Stumpe, Wu, Narayanaswamy, Venugopalan, Widner, Madams, Cuadros (bib0039) 2016; 316 Szegedy (10.1016/j.patcog.2020.107332_bib0008) 2014 Pien (10.1016/j.patcog.2020.107332_bib0018) 2005; 10 Esteva (10.1016/j.patcog.2020.107332_bib0005) 2017; 542 Wang (10.1016/j.patcog.2020.107332_bib0048) 2020 Madry (10.1016/j.patcog.2020.107332_bib0027) 2018 Maaten (10.1016/j.patcog.2020.107332_bib0044) 2008; 9 Wang (10.1016/j.patcog.2020.107332_bib0047) 2019 Menze (10.1016/j.patcog.2020.107332_bib0024) 2015; 34 Metzen (10.1016/j.patcog.2020.107332_bib0036) 2017 Selvaraju (10.1016/j.patcog.2020.107332_bib0045) 2017 10.1016/j.patcog.2020.107332_bib0014 Gulshan (10.1016/j.patcog.2020.107332_bib0025) 2016 He (10.1016/j.patcog.2020.107332_bib0001) 2016 Niu (10.1016/j.patcog.2020.107332_bib0017) 2019; vol. 33 10.1016/j.patcog.2020.107332_bib0050 Li (10.1016/j.patcog.2020.107332_bib0015) 2019 Cheng (10.1016/j.patcog.2020.107332_bib0022) 2015 Ross (10.1016/j.patcog.2020.107332_bib0033) 2018 Wang (10.1016/j.patcog.2020.107332_bib0013) 2017 Ciresan (10.1016/j.patcog.2020.107332_bib0026) 2013; vol. 8150 Jiang (10.1016/j.patcog.2020.107332_bib0028) 2019 Roth (10.1016/j.patcog.2020.107332_bib0007) 2015 Wang (10.1016/j.patcog.2020.107332_bib0021) 2019 Goodfellow (10.1016/j.patcog.2020.107332_bib0009) 2015 Gu (10.1016/j.patcog.2020.107332_bib0019) 2015 Carlini (10.1016/j.patcog.2020.107332_bib0031) 2017 Ma (10.1016/j.patcog.2020.107332_bib0038) 2018 Wang (10.1016/j.patcog.2020.107332_bib0002) 2019; 16 Zhou (10.1016/j.patcog.2020.107332_bib0035) 2020; 98 Eykholt (10.1016/j.patcog.2020.107332_bib0010) 2018 Paschali (10.1016/j.patcog.2020.107332_bib0016) 2018 Wu (10.1016/j.patcog.2020.107332_bib0029) 2020 Lu (10.1016/j.patcog.2020.107332_bib0004) 2018; 40 Gulshan (10.1016/j.patcog.2020.107332_bib0039) 2016; 316 Lu (10.1016/j.patcog.2020.107332_bib0043) 2017 Cheng (10.1016/j.patcog.2020.107332_bib0011) 2018 10.1016/j.patcog.2020.107332_bib0006 Bai (10.1016/j.patcog.2020.107332_bib0003) 2018; 75 Athalye (10.1016/j.patcog.2020.107332_bib0034) 2018 Simonyan (10.1016/j.patcog.2020.107332_bib0041) 2014 Liu (10.1016/j.patcog.2020.107332_bib0023) 2014 10.1016/j.patcog.2020.107332_bib0042 10.1016/j.patcog.2020.107332_bib0049 Finlayson (10.1016/j.patcog.2020.107332_bib0012) 2019; 363 Kurakin (10.1016/j.patcog.2020.107332_bib0030) 2017 Feinman (10.1016/j.patcog.2020.107332_bib0037) 2017 Liu (10.1016/j.patcog.2020.107332_bib0046) 2019; vol. 33 Liu (10.1016/j.patcog.2020.107332_bib0020) 2019 Shafahi (10.1016/j.patcog.2020.107332_bib0040) 2019 Bai (10.1016/j.patcog.2020.107332_bib0032) 2019 |
| References_xml | – volume: 16 start-page: 310 year: 2019 end-page: 314 ident: bib0002 article-title: Multiscale visual attention networks for object detection in VHR remote sensing images publication-title: IEEE Geosci. Remote Sens. Lett. – start-page: 770 year: 2016 end-page: 778 ident: bib0001 article-title: Deep residual learning for image recognition publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 274 year: 2018 end-page: 283 ident: bib0034 article-title: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples publication-title: International Conference on Machine Learning – year: 2020 ident: bib0029 article-title: Skip connections matter: On the transferability of adversarial examples generated with resnets publication-title: International Conference on Learning Representations – volume: vol. 8150 start-page: 411 year: 2013 end-page: 418 ident: bib0026 article-title: Mitosis detection in breast cancer histology images with deep neural networks. publication-title: International Conference on Medical Image Computing and Computer Assisted Intervention – reference: ISIC, The international skin imaging collaboration, 2019, ( – reference: ). – volume: 10 start-page: 259 year: 2005 end-page: 266 ident: bib0018 article-title: Using imaging biomarkers to accelerate drug development and clinical trials publication-title: Drug Discov. Today – year: 2018 ident: bib0033 article-title: Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients publication-title: Thirty-Second AAAI Conference on Artificial Intelligence – year: 2020 ident: bib0048 article-title: Improving adversarial robustness requires revisiting misclassified examples publication-title: International Conference on Learning Representations – start-page: 111 year: 2019 end-page: 119 ident: bib0020 article-title: Unsupervised ensemble strategy for retinal vessel segmentation publication-title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 – volume: vol. 33 start-page: 1028 year: 2019 end-page: 1035 ident: bib0046 article-title: Perceptual-sensitive GAN for generating adversarial patches publication-title: AAAI Conference on Artificial Intelligence – start-page: 69 year: 2019 end-page: 91 ident: bib0015 article-title: Volumetric medical image segmentation: a 3d deep coarse-to-fine framework and its adversarial examples publication-title: Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics – year: 2018 ident: bib0038 article-title: Characterizing adversarial subspaces using local intrinsic dimensionality publication-title: International Conference on Learning Representations – start-page: 4784 year: 2019 end-page: 4793 ident: bib0032 article-title: Hilbert-based generative defense for adversarial examples publication-title: IEEE International Conference on Computer Vision – start-page: 6586 year: 2019 end-page: 6595 ident: bib0047 article-title: On the convergence and robustness of adversarial training publication-title: International Conference on Machine Learning – year: 2017 ident: bib0037 article-title: Detecting adversarial samples from artifacts publication-title: International Conference on Learning Representations – volume: 9 start-page: 2579 year: 2008 end-page: 2605 ident: bib0044 article-title: Visualizing data using t-SNE publication-title: J. Mach. Learn. Res. – start-page: 1625 year: 2018 end-page: 1634 ident: bib0010 article-title: Robust physical-world attacks on deep learning visual classification publication-title: IEEE Conference on Computer Vision and Pattern Recognition – reference: H. Yu, A. Liu, X. Liu, J. Yang, C. Zhang, Towards noise-robust neural networks via progressive adversarial training, arXiv: – start-page: 39 year: 2017 end-page: 57 ident: bib0031 article-title: Towards evaluating the robustness of neural networks publication-title: 2017 IEEE Symposium on Security and Privacy – year: 2017 ident: bib0036 article-title: On detecting adversarial perturbations publication-title: International Conference on Learning Representations – start-page: 864 year: 2019 end-page: 872 ident: bib0028 article-title: Black-box adversarial attacks on video recognition models publication-title: ACM International Conference on Multimedia – start-page: 3353 year: 2019 end-page: 3364 ident: bib0040 article-title: Adversarial training for free! publication-title: Advances in Neural Information Processing Systems – start-page: 556 year: 2015 end-page: 564 ident: bib0007 article-title: DeepOrgan: multi-level deep convolutional networks for automated pancreas segmentation publication-title: International Conference on Medical Image Computing and Computer Assisted Intervention – year: 2015 ident: bib0022 article-title: Deep similarity learning for multimodal medical images publication-title: Comput. Methods Biomech. Biomed.Eng. – year: 2018 ident: bib0027 article-title: Towards deep learning models resistant to adversarial attacks publication-title: International Conference on Learning Representations – start-page: 1015 year: 2014 end-page: 1018 ident: bib0023 article-title: Early/diagnosis of Alzheimer’s disease with deep learning publication-title: IEEE International Symposium on Biomedical Imaging (ISBI) – volume: 98 start-page: 107040 year: 2020 ident: bib0035 article-title: Learning binary code for fast nearest subspace search publication-title: Pattern Recognit. – start-page: 618 year: 2017 end-page: 626 ident: bib0045 article-title: Grad-CAM: visual explanations from deep networks via gradient-based localization publication-title: International Conference on Computer Vision – year: 2017 ident: bib0030 article-title: Adversarial examples in the physical world publication-title: International Conference on Learning Representations – volume: 316 start-page: 2402 year: 2016 end-page: 2410 ident: bib0039 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: Jama – reference: C. Zhang, A. Liu, X. Liu, Y. Xu, H. Yu, Y. Ma, T. Li, Interpreting and improving adversarial robustness with neuron sensitivity, arXiv: – reference: (2017). – year: 2015 ident: bib0019 article-title: Learning to boost filamentary structure segmentation publication-title: International Conference on Computer Vision – year: 2015 ident: bib0009 article-title: Explaining and harnessing adversarial examples publication-title: International Conference on Learning Representations – reference: F. Tramèr, N. Papernot, I. Goodfellow, D. Boneh, P. McDaniel, The space of transferable adversarial examples, arXiv: – start-page: 446 year: 2017 end-page: 454 ident: bib0043 article-title: SafetyNet: detecting and rejecting adversarial examples robustly publication-title: International Conference on Computer Vision – volume: 40 start-page: 221 year: 2018 end-page: 234 ident: bib0004 article-title: SymPS: BRDF symmetry guided photometric stereo for shape and light source estimation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. (TPAMI) – reference: (2019). – year: 2019 ident: bib0021 article-title: Abdominal multi-organ segmentation with organ-attention networks and statistical fusion publication-title: Med. Image Anal. – year: 2016 ident: bib0025 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: J. Am. Med. Assoc. – start-page: 105 year: 2018 end-page: 121 ident: bib0011 article-title: Appearance-based gaze estimation via evaluation-guided asymmetric regression publication-title: European Conference on Computer Vision (ECCV) – volume: 75 start-page: 136 year: 2018 end-page: 148 ident: bib0003 article-title: Adaptive hash retrieval with kernel based similarity publication-title: Pattern Recognit. – volume: 34 start-page: 1993 year: 2015 end-page: 2024 ident: bib0024 article-title: The multimodal brain tumor image segmentation benchmark (brats) publication-title: IEEE Trans. Med. Imaging – volume: 363 start-page: 1287 year: 2019 end-page: 1289 ident: bib0012 article-title: Adversarial attacks on medical machine learning publication-title: Science – start-page: 493 year: 2018 end-page: 501 ident: bib0016 article-title: Generalizability vs. Robustness: investigating medical imaging networks using adversarial examples publication-title: Medical Image Computing and Computer Assisted Intervention – start-page: 3462 year: 2017 end-page: 3471 ident: bib0013 article-title: ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases publication-title: IEEE Conference on Computer Vision and Pattern Recognition – volume: 542 start-page: 115 year: 2017 ident: bib0005 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature – volume: vol. 33 start-page: 1093 year: 2019 end-page: 1101 ident: bib0017 article-title: Pathological evidence exploration in deep retinal image diagnosis publication-title: AAAI Conference on Artificial Intelligence – year: 2014 ident: bib0008 article-title: Intriguing properties of neural networks publication-title: International Conference on Learning Representations – reference: Kaggle, Kaggle diabetic retinopathy detection challenge, 2015, ( – year: 2014 ident: bib0041 article-title: Deep inside convolutional networks: Visualising image classification models and saliency maps publication-title: International Conference on Learning Representations, Workshop Track Proceedings – start-page: 69 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0015 article-title: Volumetric medical image segmentation: a 3d deep coarse-to-fine framework and its adversarial examples – start-page: 39 year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0031 article-title: Towards evaluating the robustness of neural networks – year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0033 article-title: Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients – ident: 10.1016/j.patcog.2020.107332_bib0049 – volume: 542 start-page: 115 issue: 7639 year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0005 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature doi: 10.1038/nature21056 – volume: 98 start-page: 107040 year: 2020 ident: 10.1016/j.patcog.2020.107332_bib0035 article-title: Learning binary code for fast nearest subspace search publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2019.107040 – start-page: 105 year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0011 article-title: Appearance-based gaze estimation via evaluation-guided asymmetric regression – year: 2014 ident: 10.1016/j.patcog.2020.107332_bib0008 article-title: Intriguing properties of neural networks – volume: 34 start-page: 1993 issue: 10 year: 2015 ident: 10.1016/j.patcog.2020.107332_bib0024 article-title: The multimodal brain tumor image segmentation benchmark (brats) publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2014.2377694 – year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0030 article-title: Adversarial examples in the physical world – volume: 16 start-page: 310 issue: 2 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0002 article-title: Multiscale visual attention networks for object detection in VHR remote sensing images publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2018.2872355 – start-page: 618 year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0045 article-title: Grad-CAM: visual explanations from deep networks via gradient-based localization – volume: vol. 8150 start-page: 411 year: 2013 ident: 10.1016/j.patcog.2020.107332_bib0026 article-title: Mitosis detection in breast cancer histology images with deep neural networks. – year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0036 article-title: On detecting adversarial perturbations – start-page: 3353 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0040 article-title: Adversarial training for free! – start-page: 3462 year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0013 article-title: ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases – volume: vol. 33 start-page: 1093 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0017 article-title: Pathological evidence exploration in deep retinal image diagnosis – start-page: 556 year: 2015 ident: 10.1016/j.patcog.2020.107332_bib0007 article-title: DeepOrgan: multi-level deep convolutional networks for automated pancreas segmentation – ident: 10.1016/j.patcog.2020.107332_bib0006 – volume: 9 start-page: 2579 issue: Nov year: 2008 ident: 10.1016/j.patcog.2020.107332_bib0044 article-title: Visualizing data using t-SNE publication-title: J. Mach. Learn. Res. – volume: 40 start-page: 221 issue: 1 year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0004 article-title: SymPS: BRDF symmetry guided photometric stereo for shape and light source estimation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. (TPAMI) doi: 10.1109/TPAMI.2017.2655525 – year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0038 article-title: Characterizing adversarial subspaces using local intrinsic dimensionality – start-page: 6586 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0047 article-title: On the convergence and robustness of adversarial training – volume: 10 start-page: 259 issue: 4 year: 2005 ident: 10.1016/j.patcog.2020.107332_bib0018 article-title: Using imaging biomarkers to accelerate drug development and clinical trials publication-title: Drug Discov. Today doi: 10.1016/S1359-6446(04)03334-3 – year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0021 article-title: Abdominal multi-organ segmentation with organ-attention networks and statistical fusion publication-title: Med. Image Anal. doi: 10.1016/j.media.2019.04.005 – year: 2015 ident: 10.1016/j.patcog.2020.107332_bib0009 article-title: Explaining and harnessing adversarial examples – year: 2020 ident: 10.1016/j.patcog.2020.107332_bib0029 article-title: Skip connections matter: On the transferability of adversarial examples generated with resnets – start-page: 864 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0028 article-title: Black-box adversarial attacks on video recognition models – start-page: 4784 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0032 article-title: Hilbert-based generative defense for adversarial examples – start-page: 446 year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0043 article-title: SafetyNet: detecting and rejecting adversarial examples robustly – year: 2016 ident: 10.1016/j.patcog.2020.107332_bib0025 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: J. Am. Med. Assoc. doi: 10.1001/jama.2016.17216 – ident: 10.1016/j.patcog.2020.107332_bib0014 – start-page: 493 year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0016 article-title: Generalizability vs. Robustness: investigating medical imaging networks using adversarial examples – year: 2014 ident: 10.1016/j.patcog.2020.107332_bib0041 article-title: Deep inside convolutional networks: Visualising image classification models and saliency maps publication-title: International Conference on Learning Representations, Workshop Track Proceedings – start-page: 770 year: 2016 ident: 10.1016/j.patcog.2020.107332_bib0001 article-title: Deep residual learning for image recognition – start-page: 274 year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0034 article-title: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples – year: 2017 ident: 10.1016/j.patcog.2020.107332_bib0037 article-title: Detecting adversarial samples from artifacts – year: 2015 ident: 10.1016/j.patcog.2020.107332_bib0019 article-title: Learning to boost filamentary structure segmentation – year: 2020 ident: 10.1016/j.patcog.2020.107332_bib0048 article-title: Improving adversarial robustness requires revisiting misclassified examples – volume: vol. 33 start-page: 1028 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0046 article-title: Perceptual-sensitive GAN for generating adversarial patches – volume: 316 start-page: 2402 issue: 22 year: 2016 ident: 10.1016/j.patcog.2020.107332_bib0039 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: Jama doi: 10.1001/jama.2016.17216 – ident: 10.1016/j.patcog.2020.107332_bib0050 – start-page: 1625 year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0010 article-title: Robust physical-world attacks on deep learning visual classification – volume: 363 start-page: 1287 issue: 6433 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0012 article-title: Adversarial attacks on medical machine learning publication-title: Science doi: 10.1126/science.aaw4399 – ident: 10.1016/j.patcog.2020.107332_bib0042 – year: 2015 ident: 10.1016/j.patcog.2020.107332_bib0022 article-title: Deep similarity learning for multimodal medical images publication-title: Comput. Methods Biomech. Biomed.Eng. – year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0027 article-title: Towards deep learning models resistant to adversarial attacks – start-page: 111 year: 2019 ident: 10.1016/j.patcog.2020.107332_bib0020 article-title: Unsupervised ensemble strategy for retinal vessel segmentation – volume: 75 start-page: 136 year: 2018 ident: 10.1016/j.patcog.2020.107332_bib0003 article-title: Adaptive hash retrieval with kernel based similarity publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.03.020 – start-page: 1015 year: 2014 ident: 10.1016/j.patcog.2020.107332_bib0023 article-title: Early/diagnosis of Alzheimer’s disease with deep learning |
| SSID | ssj0017142 |
| Score | 2.723356 |
| Snippet | •Medical image DNNs are easier to be attacked than natural non-medical image DNNs.•Complex biological textures of medical images may lead to more vulnerable... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 107332 |
| SubjectTerms | Adversarial attack Adversarial example detection Deep learning Medical image analysis |
| Title | Understanding adversarial attacks on deep learning based medical image analysis systems |
| URI | https://dx.doi.org/10.1016/j.patcog.2020.107332 |
| Volume | 110 |
| WOSCitedRecordID | wos000585304300008&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-5142 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017142 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELYocOillAKCPpAPvVWpNnYSJ0dUgdoKVkjlsT1FTuzQXZXsiiQVP79je5zdFYgWJC7RyoqTlefL55nxPAj5yAoVJzIrA5ZoAQYK8KCMWBmoIkxhP1YDbaPdL47FcJiORtkpxs83tp2AqOv09jabPauoYQyEbVJnHyHu_qEwAL9B6HAFscP1vwR_vpSuIk3D5Uba3hyybU1GvTkfUFrPfMeIq09mK1PumN3U4Lg2cTzSVytpFmqaoxZ7aotymkQYjD6an-WfWGV0BE-ddP3gcNxZqu9-yWkf8NOhS2Du0ne083PcYHoaOiNY6OOXvYfMZ8nMQ5Is6_Iw4GzgiEw7ok0FD0BZW2ZiF-F6h9Wdg2HyeQa70_QKjHpmBgVHz-hyvewfrhylaQwP5MVj8YKsMRFnQHlrB98OR9_7QyYRRq6YPP49n1lpw__uvut-zWVBGzl7TV6hGUEPnPg3yYqu35AN36KDImNvkcslNNAFNFBEA53W1KCBejRQiwaKaKAWDdSjgSIatsn50eHZl68B9tIISlCx26AQvEw5ELjMdBhrOahKDrqoOZdlkkutCi5DFVbA4UVVZIUqSl7JLNJKDVQSVXyHrNbTWu8SmuoqEjJJ4DawB4SZZz5sMNNiwUKu9gj365SXWGje9Dv5nfuIwknuVjc3q5u71d0jQT9r5gqt_ON-4UWQo7LolMAcUPPgzLdPnvmOvJyD_j1ZbW86_YGsl3_acXOzj_D6CwU3kdk |
| linkProvider | Elsevier |
| 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=Understanding+adversarial+attacks+on+deep+learning+based+medical+image+analysis+systems&rft.jtitle=Pattern+recognition&rft.au=Ma%2C+Xingjun&rft.au=Niu%2C+Yuhao&rft.au=Gu%2C+Lin&rft.au=Wang%2C+Yisen&rft.date=2021-02-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.eissn=1873-5142&rft.volume=110&rft_id=info:doi/10.1016%2Fj.patcog.2020.107332&rft.externalDocID=S0031320320301357 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |