Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection
Previous studies have adopted unsupervised machine learning with dimension reduction functions for cyberattack detection, which are limited to performing robust anomaly detection with high-dimensional and sparse data. Most of them usually assume homogeneous parameters with a specific Gaussian distri...
Gespeichert in:
| Veröffentlicht in: | Information processing & management Jg. 59; H. 2; S. 102844 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Oxford
Elsevier Ltd
01.03.2022
Elsevier Science Ltd |
| Schlagworte: | |
| ISSN: | 0306-4573, 1873-5371 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Previous studies have adopted unsupervised machine learning with dimension reduction functions for cyberattack detection, which are limited to performing robust anomaly detection with high-dimensional and sparse data. Most of them usually assume homogeneous parameters with a specific Gaussian distribution for each domain, ignoring the robust testing of data skewness. This paper proposes to use unsupervised ensemble autoencoders connected to the Gaussian mixture model (GMM) to adapt to multiple domains regardless of the skewness of each domain. In the hidden space of the ensemble autoencoder, the attention-based latent representation and reconstructed features of the minimum error are utilized. The expectation maximization (EM) algorithm is used to estimate the sample density in the GMM. When the estimated sample density exceeds the learning threshold obtained in the training phase, the sample is identified as an outlier related to an attack anomaly. Finally, the ensemble autoencoder and the GMM are jointly optimized, which transforms the optimization of objective function into a Lagrangian dual problem. Experiments conducted on three public data sets validate that the performance of the proposed model is significantly competitive with the selected anomaly detection baselines.
•An ensemble framework of multichannel network anomaly detection model that combines deep autoencoders and the GMM.•A robust optimization version of EM3 for multiple domains, which transforms the optimization problem of the objective function into a Lagrangian dual.•We deduce the formula and analyze the convergence of the full text, and prove that our model has stability and robustness.•To the best of our knowledge is the first work that performs algorithms on both differentiated data domains and data distributions. |
|---|---|
| AbstractList | Previous studies have adopted unsupervised machine learning with dimension reduction functions for cyberattack detection, which are limited to performing robust anomaly detection with high-dimensional and sparse data. Most of them usually assume homogeneous parameters with a specific Gaussian distribution for each domain, ignoring the robust testing of data skewness. This paper proposes to use unsupervised ensemble autoencoders connected to the Gaussian mixture model (GMM) to adapt to multiple domains regardless of the skewness of each domain. In the hidden space of the ensemble autoencoder, the attention-based latent representation and reconstructed features of the minimum error are utilized. The expectation maximization (EM) algorithm is used to estimate the sample density in the GMM. When the estimated sample density exceeds the learning threshold obtained in the training phase, the sample is identified as an outlier related to an attack anomaly. Finally, the ensemble autoencoder and the GMM are jointly optimized, which transforms the optimization of objective function into a Lagrangian dual problem. Experiments conducted on three public data sets validate that the performance of the proposed model is significantly competitive with the selected anomaly detection baselines.
•An ensemble framework of multichannel network anomaly detection model that combines deep autoencoders and the GMM.•A robust optimization version of EM3 for multiple domains, which transforms the optimization problem of the objective function into a Lagrangian dual.•We deduce the formula and analyze the convergence of the full text, and prove that our model has stability and robustness.•To the best of our knowledge is the first work that performs algorithms on both differentiated data domains and data distributions. Previous studies have adopted unsupervised machine learning with dimension reduction functions for cyberattack detection, which are limited to performing robust anomaly detection with high-dimensional and sparse data. Most of them usually assume homogeneous parameters with a specific Gaussian distribution for each domain, ignoring the robust testing of data skewness. This paper proposes to use unsupervised ensemble autoencoders connected to the Gaussian mixture model (GMM) to adapt to multiple domains regardless of the skewness of each domain. In the hidden space of the ensemble autoencoder, the attention-based latent representation and reconstructed features of the minimum error are utilized. The expectation maximization (EM) algorithm is used to estimate the sample density in the GMM. When the estimated sample density exceeds the learning threshold obtained in the training phase, the sample is identified as an outlier related to an attack anomaly. Finally, the ensemble autoencoder and the GMM are jointly optimized, which transforms the optimization of objective function into a Lagrangian dual problem. Experiments conducted on three public data sets validate that the performance of the proposed model is significantly competitive with the selected anomaly detection baselines. |
| ArticleNumber | 102844 |
| Author | An, Peng Wang, Zhiyuan Zhang, Chunjiong |
| Author_xml | – sequence: 1 givenname: Peng surname: An fullname: An, Peng organization: College of Electronics and Information Engineering, Ningbo University of Technology, Ningbo 315211, Zhejiang, PR China – sequence: 2 givenname: Zhiyuan orcidid: 0000-0001-9638-6515 surname: Wang fullname: Wang, Zhiyuan organization: International College of Football, Tongji University, Shanghai 200092, PR China – sequence: 3 givenname: Chunjiong orcidid: 0000-0002-6711-3486 surname: Zhang fullname: Zhang, Chunjiong email: chunjiongzhang@tongji.edu.cn organization: Department of Computer Science, Tongji University, Shanghai 201804, PR China |
| BookMark | eNp9kEtrGzEQgEVJIE6aH5CboOd19dxdk1MJiRMI5NLSo5iVRiDXKzmSNjT_PjLuqYechmHmm8d3Sc5iikjIDWdrznj_fbcOh3ktmOAtF6NSX8iKj4PstBz4GVkxyfpO6UFekMtSdowxpblYkd_3seA87ZEusSwHzG-hoKOw1ITRJoe5UIiObmEpJUCkc_hbl4x0brU99SlT-z5hhlrB_qEOK9oaUvxKzj3sC17_i1fk18P9z7vH7vll-3T347mzUujaCZi4R60UE8yraeyFRWB-BI_jyNgE0klgfNISJ9TOOu-kFeD6YQPCK5RX5Ntp7iGn1wVLNbu05NhWGtErrseN3oytazh12ZxKyeiNDRWOd9YMYW84M0eLZmeaRXO0aE4WG8n_Iw85zJDfP2VuTwy2x98CZlNsaDbRhdzsGJfCJ_QHhLuOxw |
| CitedBy_id | crossref_primary_10_1155_2022_5212585 crossref_primary_10_1007_s10618_025_01131_5 crossref_primary_10_1002_joc_8618 crossref_primary_10_1155_2022_8328378 crossref_primary_10_1155_2022_7244001 crossref_primary_10_51889_2959_5894_2024_86_2_018 crossref_primary_10_1155_2022_3848836 crossref_primary_10_1155_2022_2097422 crossref_primary_10_1016_j_iot_2024_101342 crossref_primary_10_1155_2022_1153080 crossref_primary_10_1155_2022_1859020 crossref_primary_10_1155_2022_7646452 crossref_primary_10_1155_2022_9263736 crossref_primary_10_1155_2022_9208172 crossref_primary_10_3390_fi15050187 crossref_primary_10_1007_s10462_023_10662_6 crossref_primary_10_1007_s43538_023_00205_6 crossref_primary_10_1155_2022_3832935 crossref_primary_10_1155_2022_4135519 crossref_primary_10_1155_2022_4268982 crossref_primary_10_1155_2022_9190687 crossref_primary_10_1155_2022_4326551 crossref_primary_10_1155_2022_1104633 crossref_primary_10_1155_2022_2779909 crossref_primary_10_1155_2022_4875859 crossref_primary_10_1155_2022_9011311 crossref_primary_10_1155_2022_5295115 crossref_primary_10_1177_01423312241284660 crossref_primary_10_1155_2022_9517615 crossref_primary_10_1155_2022_2286803 crossref_primary_10_1155_2022_2899128 crossref_primary_10_1155_2022_7079045 crossref_primary_10_1155_2022_7765024 crossref_primary_10_1155_2022_8411550 crossref_primary_10_1109_TIV_2024_3369851 crossref_primary_10_1155_2022_3198565 crossref_primary_10_1155_2022_8396348 crossref_primary_10_1155_2022_3447851 crossref_primary_10_1186_s13635_023_00139_y crossref_primary_10_1155_2022_2084606 crossref_primary_10_1155_2022_4560697 crossref_primary_10_1007_s00500_023_08985_1 crossref_primary_10_1155_2022_7104750 crossref_primary_10_1155_2022_7122846 crossref_primary_10_1155_2022_7773157 crossref_primary_10_1155_2022_8460433 crossref_primary_10_1155_2022_8224184 crossref_primary_10_1016_j_ipm_2023_103476 crossref_primary_10_1155_2022_8168396 crossref_primary_10_1155_2022_1068467 crossref_primary_10_1155_2022_4261240 crossref_primary_10_3390_s22176659 crossref_primary_10_1155_2022_4066761 crossref_primary_10_1155_2022_4680905 crossref_primary_10_1145_3675405 crossref_primary_10_1155_2022_1971341 crossref_primary_10_1155_2023_3898063 crossref_primary_10_1155_2022_1518447 crossref_primary_10_1155_2022_2184600 crossref_primary_10_1155_2022_3643799 crossref_primary_10_1155_2022_4980893 crossref_primary_10_1007_s11370_025_00629_7 crossref_primary_10_1155_2022_3365161 crossref_primary_10_1155_2022_7628124 crossref_primary_10_1016_j_patcog_2023_110193 crossref_primary_10_1155_2022_5485284 crossref_primary_10_3390_e25071065 crossref_primary_10_1016_j_istruc_2025_109052 crossref_primary_10_1155_2022_2035662 crossref_primary_10_1155_2022_6097834 crossref_primary_10_1007_s10922_023_09767_8 crossref_primary_10_1155_2022_7125462 crossref_primary_10_1155_2022_6490194 crossref_primary_10_1007_s11630_024_2075_0 crossref_primary_10_1016_j_engfracmech_2024_110699 crossref_primary_10_1155_2022_7833292 crossref_primary_10_1155_2022_8566454 crossref_primary_10_1155_2022_8925907 crossref_primary_10_1007_s11222_025_10621_x crossref_primary_10_1016_j_apenergy_2025_125768 crossref_primary_10_1155_2022_1797080 crossref_primary_10_1155_2022_1056869 crossref_primary_10_1155_2022_1086817 crossref_primary_10_1155_2022_8566721 crossref_primary_10_1007_s10115_024_02172_w crossref_primary_10_1155_2022_6711470 crossref_primary_10_1109_TCE_2024_3519437 crossref_primary_10_1109_TDSC_2024_3418906 crossref_primary_10_1155_2022_7747192 crossref_primary_10_1007_s10489_024_05602_y crossref_primary_10_1155_2022_2179494 crossref_primary_10_1016_j_ipm_2025_104238 crossref_primary_10_1155_2022_4508507 crossref_primary_10_3390_e26090762 crossref_primary_10_1155_2022_5862204 crossref_primary_10_1155_2022_8958865 crossref_primary_10_1155_2022_5350786 crossref_primary_10_1155_2022_6361098 crossref_primary_10_1155_2022_5035369 crossref_primary_10_1155_2022_2333497 crossref_primary_10_1155_2022_3548854 crossref_primary_10_1155_2022_7564988 crossref_primary_10_1155_2022_2779686 crossref_primary_10_1155_2022_3702479 crossref_primary_10_1049_ntw2_12134 crossref_primary_10_1155_2022_1681657 crossref_primary_10_1109_ACCESS_2024_3360691 crossref_primary_10_1155_2022_6518521 crossref_primary_10_1155_2022_7135043 crossref_primary_10_1155_2022_8077277 crossref_primary_10_1109_JSEN_2024_3363767 crossref_primary_10_1155_2022_3109468 crossref_primary_10_1515_apjri_2024_0002 crossref_primary_10_1007_s10489_024_05654_0 crossref_primary_10_1155_2022_8409780 crossref_primary_10_1155_2022_1113023 crossref_primary_10_1155_2022_5028705 crossref_primary_10_1155_2022_3127698 crossref_primary_10_1155_2022_9717449 crossref_primary_10_1155_2022_7173421 crossref_primary_10_1155_2022_7609195 crossref_primary_10_1155_2022_7665954 crossref_primary_10_1007_s40031_024_01049_4 crossref_primary_10_1016_j_engappai_2023_107706 crossref_primary_10_1155_2022_5109638 crossref_primary_10_1155_2022_9328712 crossref_primary_10_1155_2022_2278683 crossref_primary_10_1155_2022_9585760 crossref_primary_10_3390_sym14020409 crossref_primary_10_1155_2022_7247932 crossref_primary_10_1155_2022_5501322 crossref_primary_10_1177_00405175231171720 crossref_primary_10_1016_j_neunet_2025_107416 crossref_primary_10_1007_s10207_025_01000_8 crossref_primary_10_1155_2022_8595203 crossref_primary_10_1155_2022_2850604 crossref_primary_10_1155_2022_3387543 crossref_primary_10_1155_2022_5820145 crossref_primary_10_1155_2022_7068596 crossref_primary_10_1371_journal_pone_0317042 crossref_primary_10_1155_2022_1219802 crossref_primary_10_1155_2022_6825863 crossref_primary_10_1155_2022_9086938 crossref_primary_10_1142_S0218126625501634 crossref_primary_10_1155_2022_1022421 crossref_primary_10_1155_2022_4117957 crossref_primary_10_3390_land13071039 crossref_primary_10_1155_2022_5813577 crossref_primary_10_1155_2022_1857304 crossref_primary_10_1016_j_eswa_2024_123675 crossref_primary_10_1155_2022_1230786 crossref_primary_10_1155_2022_6737194 crossref_primary_10_1155_2022_2281469 crossref_primary_10_1155_2022_4861684 crossref_primary_10_1016_j_asoc_2024_111423 crossref_primary_10_1155_2022_6245984 crossref_primary_10_1155_2022_1110698 crossref_primary_10_2478_amns_2023_2_00097 crossref_primary_10_1007_s11356_024_32170_y crossref_primary_10_1080_10618600_2024_2414889 crossref_primary_10_1002_spe_3407 crossref_primary_10_1016_j_datak_2025_102430 crossref_primary_10_1155_2022_5875380 crossref_primary_10_1016_j_inffus_2024_102922 crossref_primary_10_1155_2022_6023784 crossref_primary_10_1155_2022_5696334 crossref_primary_10_1186_s13662_025_03925_9 crossref_primary_10_1155_2022_2787994 crossref_primary_10_1155_2022_4033886 crossref_primary_10_1155_2022_3077453 crossref_primary_10_1155_2022_3713891 crossref_primary_10_1155_2022_7581079 crossref_primary_10_1155_2022_4879361 crossref_primary_10_1155_2022_1682147 crossref_primary_10_1155_2022_8169938 crossref_primary_10_1016_j_patcog_2024_110846 crossref_primary_10_1155_2022_5220916 crossref_primary_10_1155_2022_8730399 crossref_primary_10_1155_2022_5855328 crossref_primary_10_1007_s13369_025_10501_6 crossref_primary_10_1155_2022_6708033 crossref_primary_10_1155_2022_4152884 crossref_primary_10_1016_j_iot_2025_101518 crossref_primary_10_1016_j_jenvman_2023_118846 crossref_primary_10_1155_2022_6823102 crossref_primary_10_1371_journal_pone_0330421 crossref_primary_10_1002_cpe_7718 crossref_primary_10_1155_2022_8294254 crossref_primary_10_1155_2022_7126743 |
| Cites_doi | 10.1109/ICCV.2019.00047 10.1109/MNET.2019.1800358 10.1109/CVPR.2018.00086 10.1016/j.physleta.2005.11.005 10.1109/TNSM.2016.2627340 10.1109/ICCV.2019.00179 10.1016/j.neucom.2017.04.014 10.1609/aaai.v33i01.33014739 10.1145/3097983.3098052 10.1109/CVPR.2018.00417 10.1109/TETCI.2017.2772792 10.1109/TNNLS.2019.2905082 10.1016/j.measurement.2019.107232 10.1016/j.ins.2017.04.044 |
| ContentType | Journal Article |
| Copyright | 2021 Copyright Elsevier Science Ltd. Mar 2022 |
| Copyright_xml | – notice: 2021 – notice: Copyright Elsevier Science Ltd. Mar 2022 |
| DBID | AAYXX CITATION E3H F2A |
| DOI | 10.1016/j.ipm.2021.102844 |
| DatabaseName | CrossRef Library & Information Sciences Abstracts (LISA) Library & Information Science Abstracts (LISA) |
| DatabaseTitle | CrossRef Library and Information Science Abstracts (LISA) |
| DatabaseTitleList | Library and Information Science Abstracts (LISA) |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Library & Information Science |
| EISSN | 1873-5371 |
| ExternalDocumentID | 10_1016_j_ipm_2021_102844 S0306457321003162 |
| GroupedDBID | --K --M -~X .DC .~1 0B8 0R~ 1B1 1RT 1~. 1~5 29I 4.4 41~ 457 4G. 5GY 5VS 7-5 71M 77K 8P~ 9JN 9JO AABNK AACTN AAEDT AAEDW AAFJI AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN AAYOK ABBOA ABFNM ABFRF ABJNI ABMAC ABMMH ABPPZ ABXDB ABYKQ ACDAQ ACGFS ACHQT ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD AEBSH AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV AKYCK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOMHK AOUOD ASPBG AVARZ AVWKF AXJTR AZFZN BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HMY HVGLF HZ~ H~9 IHE J1W KOM LG9 LPU LY1 M3Y M41 MO0 MS~ MVM N9A O-L O9- OAUVE OHT OZT P-8 P-9 P2P PC. PQQKQ PRBVW Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSO SSS SSV SSZ T5K TN5 U5U UHB UHS UNMZH WUQ XFK ZMT ~G- 77I 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADMHG ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD E3H F2A |
| ID | FETCH-LOGICAL-c325t-2ab1fe544020f4b862cea0f8afe8800ba3d3a01b53ebe5dcdfd3c2ad679a2f4e3 |
| ISICitedReferencesCount | 209 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000744117200003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0306-4573 |
| IngestDate | Fri Nov 14 18:45:01 EST 2025 Sat Nov 29 07:23:45 EST 2025 Tue Nov 18 22:25:17 EST 2025 Fri Feb 23 02:41:53 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | Multidomain data Cyberattacks GMM Deep autoencoder |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c325t-2ab1fe544020f4b862cea0f8afe8800ba3d3a01b53ebe5dcdfd3c2ad679a2f4e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-9638-6515 0000-0002-6711-3486 |
| PQID | 2641589598 |
| PQPubID | 46166 |
| ParticipantIDs | proquest_journals_2641589598 crossref_citationtrail_10_1016_j_ipm_2021_102844 crossref_primary_10_1016_j_ipm_2021_102844 elsevier_sciencedirect_doi_10_1016_j_ipm_2021_102844 |
| PublicationCentury | 2000 |
| PublicationDate | March 2022 2022-03-00 20220301 |
| PublicationDateYYYYMMDD | 2022-03-01 |
| PublicationDate_xml | – month: 03 year: 2022 text: March 2022 |
| PublicationDecade | 2020 |
| PublicationPlace | Oxford |
| PublicationPlace_xml | – name: Oxford |
| PublicationTitle | Information processing & management |
| PublicationYear | 2022 |
| Publisher | Elsevier Ltd Elsevier Science Ltd |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier Science Ltd |
| References | Schoenauer-Sebag, Heinrich, Schoenauer, Sebag, Wu, Altschuler (b24) 2019 (pp. 665–674). Fourure, Emonet, Fromont, Muselet, Neverova, Trémeau (b5) 2017; 251 Luong, Pham, Manning (b15) 2015 Zong, Song, Min, Cheng, Lumezanu, Cho (b34) 2018 Liao, Guo, Chen, Li (b13) 2018 Injadat, Moubayed, Nassif, Shami (b9) 2020 Yu (b30) 2020; 67 Berriel, R., Lathuillere, S., Nabi, M., Klein, T., Oliveira-Santos, T., & Sebe, N., et al. (2019). Budget-aware adapters for multi-domain learning. In Xu, Qian, Hu (b29) 2019; 33 Zhang, Li, Gao, Chen, Li (b32) 2020; 151 Dromard, Roudière, Owezarski (b4) 2016; 14 Mariño, Míguez (b18) 2006; 351 Rezvy, Petridis, Lasebae, Zebin (b23) 2018 Zhou, C., & Paffenroth, R. C. (2017). Anomaly detection with robust deep autoencoders. In (pp. 3964–3973). (pp. 1705–1714). (pp. 762–771). Pratama, Kang (b20) 2020 Injadat, Moubayed, Shami (b10) 2020 Mahdavifar, Kadir, Fatemi, Alhadidi, Ghorbani (b16) 2020 Andresini, Appice, Di Mauro, Loglisci, Malerba (b1) 2019 Peng, Dredze (b19) 2016 Majumdar, Tripathi (b17) 2017 Ganin, Ustinova, Ajakan, Germain, Larochelle, Laviolette (b6) 2016; 17 Vaca, Niyaz (b26) 2018 Shone, Ngoc, Phai, Shi (b25) 2018; 2 Ren, Z., & Lee, Y. J. (2018). Cross-domain self-supervised multi-task feature learning using synthetic imagery. In Liu, Li, Zhou, Jiang, Sun, Wang (b14) 2020; 32 (pp. 382–391). Qian, Q., Zhu, S., Tang, J., Jin, R., Sun, B., & Li, H. (2019). Robust optimization over multiple domains. In Li, Zou, Zhong (b12) 2020 (pp. 4739–4746). Hu, Li, Liu, Li (b8) 2020; 31 Kim, Kwon, Chang, Paik (b11) 2020 Chen, Yan, Han, Wang, Peng, Wang (b3) 2018; 433 Gong, D., Liu, L., Le, V., Saha, B., Mansour, M. R., & Venkatesh, S., et al. (2019). Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In Xu, R., Chen, Z., Zuo, W., Yan, J., & Lin, L. (2018). Deep cocktail network: Multi-source unsupervised domain adaptation with category shift. In Wang, Xu, Huang, Wang, Lai (b27) 2018 Zenati, Romain, Foo, Lecouat, Chandrasekhar (b31) 2018 Xu (10.1016/j.ipm.2021.102844_b29) 2019; 33 Fourure (10.1016/j.ipm.2021.102844_b5) 2017; 251 Wang (10.1016/j.ipm.2021.102844_b27) 2018 Shone (10.1016/j.ipm.2021.102844_b25) 2018; 2 Vaca (10.1016/j.ipm.2021.102844_b26) 2018 Kim (10.1016/j.ipm.2021.102844_b11) 2020 Andresini (10.1016/j.ipm.2021.102844_b1) 2019 Injadat (10.1016/j.ipm.2021.102844_b10) 2020 Majumdar (10.1016/j.ipm.2021.102844_b17) 2017 Yu (10.1016/j.ipm.2021.102844_b30) 2020; 67 Pratama (10.1016/j.ipm.2021.102844_b20) 2020 Chen (10.1016/j.ipm.2021.102844_b3) 2018; 433 Zhang (10.1016/j.ipm.2021.102844_b32) 2020; 151 Mahdavifar (10.1016/j.ipm.2021.102844_b16) 2020 Mariño (10.1016/j.ipm.2021.102844_b18) 2006; 351 Peng (10.1016/j.ipm.2021.102844_b19) 2016 Hu (10.1016/j.ipm.2021.102844_b8) 2020; 31 Liao (10.1016/j.ipm.2021.102844_b13) 2018 10.1016/j.ipm.2021.102844_b33 Rezvy (10.1016/j.ipm.2021.102844_b23) 2018 10.1016/j.ipm.2021.102844_b2 Injadat (10.1016/j.ipm.2021.102844_b9) 2020 Li (10.1016/j.ipm.2021.102844_b12) 2020 Liu (10.1016/j.ipm.2021.102844_b14) 2020; 32 10.1016/j.ipm.2021.102844_b7 Luong (10.1016/j.ipm.2021.102844_b15) 2015 Schoenauer-Sebag (10.1016/j.ipm.2021.102844_b24) 2019 Zenati (10.1016/j.ipm.2021.102844_b31) 2018 Zong (10.1016/j.ipm.2021.102844_b34) 2018 10.1016/j.ipm.2021.102844_b28 Ganin (10.1016/j.ipm.2021.102844_b6) 2016; 17 Dromard (10.1016/j.ipm.2021.102844_b4) 2016; 14 10.1016/j.ipm.2021.102844_b21 10.1016/j.ipm.2021.102844_b22 |
| References_xml | – volume: 14 start-page: 34 year: 2016 end-page: 47 ident: b4 article-title: Online and scalable unsupervised network anomaly detection method publication-title: IEEE Transactions on Network and Service Management – volume: 351 start-page: 262 year: 2006 end-page: 267 ident: b18 article-title: An approximate gradient-descent method for joint parameter estimation and synchronization of coupled chaotic systems publication-title: Physics Letters. A – reference: (pp. 762–771). – reference: Zhou, C., & Paffenroth, R. C. (2017). Anomaly detection with robust deep autoencoders. In: – start-page: 515 year: 2020 end-page: 522 ident: b16 article-title: Dynamic android malware category classification using semi-supervised deep learning publication-title: 2020 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) – volume: 17 year: 2016 ident: b6 article-title: Domain-adversarial training of neural networks publication-title: Journal of Machine Learning Research – reference: Ren, Z., & Lee, Y. J. (2018). Cross-domain self-supervised multi-task feature learning using synthetic imagery. In: – year: 2020 ident: b12 article-title: Learning graph neural networks with approximate gradient descent – year: 2016 ident: b19 article-title: Multi-task multi-domain representation learning for sequence tagging – reference: Xu, R., Chen, Z., Zuo, W., Yan, J., & Lin, L. (2018). Deep cocktail network: Multi-source unsupervised domain adaptation with category shift. In: – volume: 433 start-page: 346 year: 2018 end-page: 364 ident: b3 article-title: Machine learning based mobile malware detection using highly imbalanced network traffic publication-title: Information Sciences – volume: 151 year: 2020 ident: b32 article-title: Intelligent fault diagnosis of rotating machinery using a new ensemble deep auto-encoder method publication-title: Measurement – reference: Qian, Q., Zhu, S., Tang, J., Jin, R., Sun, B., & Li, H. (2019). Robust optimization over multiple domains. In: – start-page: 142 year: 2018 end-page: 156 ident: b23 article-title: Intrusion detection and classification with autoencoded deep neural network publication-title: International Conference on Security for Information Technology and Communications – year: 2018 ident: b34 article-title: Deep autoencoding gaussian mixture model for unsupervised anomaly detection publication-title: International Conference on Learning Representations – reference: Berriel, R., Lathuillere, S., Nabi, M., Klein, T., Oliveira-Santos, T., & Sebe, N., et al. (2019). Budget-aware adapters for multi-domain learning. In: – reference: (pp. 1705–1714). – start-page: 727 year: 2018 end-page: 736 ident: b31 article-title: Adversarially learned anomaly detection publication-title: 2018 IEEE International Conference on Data Mining (ICDM) – start-page: 1208 year: 2018 end-page: 1217 ident: b13 article-title: A unified unsupervised gaussian mixture variational autoencoder for high dimensional outlier detection publication-title: 2018 IEEE International Conference on Big Data (Big Data) – reference: Gong, D., Liu, L., Le, V., Saha, B., Mansour, M. R., & Venkatesh, S., et al. (2019). Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: – volume: 32 start-page: 1517 year: 2020 end-page: 1528 ident: b14 article-title: Generative adversarial active learning for unsupervised outlier detection publication-title: IEEE Transactions on Knowledge and Data Engineering – reference: (pp. 665–674). – start-page: 1 year: 2020 end-page: 18 ident: b20 article-title: Trainable activation function with differentiable negative side and adaptable rectified point publication-title: Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies – start-page: 281 year: 2019 end-page: 290 ident: b1 article-title: Exploiting the auto-encoder residual error for intrusion detection publication-title: 2019 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW) – start-page: 2507 year: 2020 end-page: 2517 ident: b11 article-title: Lipschitz continuous autoencoders in application to anomaly detection publication-title: International Conference on Artificial Intelligence and Statistics – reference: (pp. 3964–3973). – volume: 31 start-page: 475 year: 2020 end-page: 487 ident: b8 article-title: Flow adversarial networks: Flowrate prediction for gas-liquid multiphase flows across different domains publication-title: IEEE Transactions on Neural Networks and Learning Systems – year: 2015 ident: b15 article-title: Effective approaches to attention-based neural machine translation – volume: 67 start-page: 2512 year: 2020 end-page: 2516 ident: b30 article-title: Optimization of combined power and modeling attacks on VR PUFs with Lagrange multipliers publication-title: IEEE Transactions on Circuits and Systems II: Express Briefs – start-page: 276 year: 2018 end-page: 286 ident: b27 article-title: Stacked discriminative denoising auto-encoder based recommender system publication-title: International Conference on Intelligent Science and Big Data Engineering – start-page: 1 year: 2020 ident: b9 article-title: Multi-stage optimized machine learning framework for network intrusion detection publication-title: IEEE Transactions on Network and Service Management – reference: (pp. 382–391). – volume: 33 start-page: 88 year: 2019 end-page: 95 ident: b29 article-title: Data-driven network intelligence for anomaly detection publication-title: IEEE Network – reference: (pp. 4739–4746). – start-page: 1 year: 2020 end-page: 4 ident: b10 article-title: Detecting botnet attacks in IoT environments: An optimized machine learning approach publication-title: 2020 32nd International Conference on Microelectronics (ICM) – start-page: 911 year: 2017 end-page: 918 ident: b17 article-title: Asymmetric stacked autoencoder publication-title: 2017 International Joint Conference on Neural Networks (IJCNN) – volume: 2 start-page: 41 year: 2018 end-page: 50 ident: b25 article-title: A deep learning approach to network intrusion detection publication-title: IEEE Transactions on Emerging Topics in Computational Intelligence – year: 2019 ident: b24 article-title: Multi-domain adversarial learning – start-page: 1 year: 2018 end-page: 5 ident: b26 article-title: An ensemble learning based wi-fi network intrusion detection system (wnids) publication-title: 2018 IEEE 17th International Symposium on Network Computing and Applications (NCA) – volume: 251 start-page: 68 year: 2017 end-page: 80 ident: b5 article-title: Multi-task, multi-domain learning: application to semantic segmentation and pose regression publication-title: Neurocomputing – ident: 10.1016/j.ipm.2021.102844_b2 doi: 10.1109/ICCV.2019.00047 – start-page: 281 year: 2019 ident: 10.1016/j.ipm.2021.102844_b1 article-title: Exploiting the auto-encoder residual error for intrusion detection – start-page: 515 year: 2020 ident: 10.1016/j.ipm.2021.102844_b16 article-title: Dynamic android malware category classification using semi-supervised deep learning – start-page: 1208 year: 2018 ident: 10.1016/j.ipm.2021.102844_b13 article-title: A unified unsupervised gaussian mixture variational autoencoder for high dimensional outlier detection – start-page: 276 year: 2018 ident: 10.1016/j.ipm.2021.102844_b27 article-title: Stacked discriminative denoising auto-encoder based recommender system – volume: 33 start-page: 88 issue: 3 year: 2019 ident: 10.1016/j.ipm.2021.102844_b29 article-title: Data-driven network intelligence for anomaly detection publication-title: IEEE Network doi: 10.1109/MNET.2019.1800358 – ident: 10.1016/j.ipm.2021.102844_b22 doi: 10.1109/CVPR.2018.00086 – start-page: 1 year: 2020 ident: 10.1016/j.ipm.2021.102844_b9 article-title: Multi-stage optimized machine learning framework for network intrusion detection publication-title: IEEE Transactions on Network and Service Management – volume: 351 start-page: 262 issue: 4–5 year: 2006 ident: 10.1016/j.ipm.2021.102844_b18 article-title: An approximate gradient-descent method for joint parameter estimation and synchronization of coupled chaotic systems publication-title: Physics Letters. A doi: 10.1016/j.physleta.2005.11.005 – start-page: 1 year: 2020 ident: 10.1016/j.ipm.2021.102844_b20 article-title: Trainable activation function with differentiable negative side and adaptable rectified point publication-title: Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies – volume: 14 start-page: 34 issue: 1 year: 2016 ident: 10.1016/j.ipm.2021.102844_b4 article-title: Online and scalable unsupervised network anomaly detection method publication-title: IEEE Transactions on Network and Service Management doi: 10.1109/TNSM.2016.2627340 – ident: 10.1016/j.ipm.2021.102844_b7 doi: 10.1109/ICCV.2019.00179 – volume: 251 start-page: 68 year: 2017 ident: 10.1016/j.ipm.2021.102844_b5 article-title: Multi-task, multi-domain learning: application to semantic segmentation and pose regression publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.04.014 – start-page: 2507 year: 2020 ident: 10.1016/j.ipm.2021.102844_b11 article-title: Lipschitz continuous autoencoders in application to anomaly detection – start-page: 142 year: 2018 ident: 10.1016/j.ipm.2021.102844_b23 article-title: Intrusion detection and classification with autoencoded deep neural network – year: 2015 ident: 10.1016/j.ipm.2021.102844_b15 – start-page: 727 year: 2018 ident: 10.1016/j.ipm.2021.102844_b31 article-title: Adversarially learned anomaly detection – volume: 67 start-page: 2512 issue: 11 year: 2020 ident: 10.1016/j.ipm.2021.102844_b30 article-title: Optimization of combined power and modeling attacks on VR PUFs with Lagrange multipliers publication-title: IEEE Transactions on Circuits and Systems II: Express Briefs – volume: 17 issue: 1 year: 2016 ident: 10.1016/j.ipm.2021.102844_b6 article-title: Domain-adversarial training of neural networks publication-title: Journal of Machine Learning Research – year: 2016 ident: 10.1016/j.ipm.2021.102844_b19 – ident: 10.1016/j.ipm.2021.102844_b21 doi: 10.1609/aaai.v33i01.33014739 – start-page: 1 year: 2018 ident: 10.1016/j.ipm.2021.102844_b26 article-title: An ensemble learning based wi-fi network intrusion detection system (wnids) – ident: 10.1016/j.ipm.2021.102844_b33 doi: 10.1145/3097983.3098052 – year: 2018 ident: 10.1016/j.ipm.2021.102844_b34 article-title: Deep autoencoding gaussian mixture model for unsupervised anomaly detection – ident: 10.1016/j.ipm.2021.102844_b28 doi: 10.1109/CVPR.2018.00417 – volume: 2 start-page: 41 issue: 1 year: 2018 ident: 10.1016/j.ipm.2021.102844_b25 article-title: A deep learning approach to network intrusion detection publication-title: IEEE Transactions on Emerging Topics in Computational Intelligence doi: 10.1109/TETCI.2017.2772792 – volume: 31 start-page: 475 issue: 2 year: 2020 ident: 10.1016/j.ipm.2021.102844_b8 article-title: Flow adversarial networks: Flowrate prediction for gas-liquid multiphase flows across different domains publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2019.2905082 – volume: 151 year: 2020 ident: 10.1016/j.ipm.2021.102844_b32 article-title: Intelligent fault diagnosis of rotating machinery using a new ensemble deep auto-encoder method publication-title: Measurement doi: 10.1016/j.measurement.2019.107232 – start-page: 911 year: 2017 ident: 10.1016/j.ipm.2021.102844_b17 article-title: Asymmetric stacked autoencoder – start-page: 1 year: 2020 ident: 10.1016/j.ipm.2021.102844_b10 article-title: Detecting botnet attacks in IoT environments: An optimized machine learning approach – volume: 433 start-page: 346 year: 2018 ident: 10.1016/j.ipm.2021.102844_b3 article-title: Machine learning based mobile malware detection using highly imbalanced network traffic publication-title: Information Sciences doi: 10.1016/j.ins.2017.04.044 – volume: 32 start-page: 1517 issue: 8 year: 2020 ident: 10.1016/j.ipm.2021.102844_b14 article-title: Generative adversarial active learning for unsupervised outlier detection publication-title: IEEE Transactions on Knowledge and Data Engineering – year: 2019 ident: 10.1016/j.ipm.2021.102844_b24 – year: 2020 ident: 10.1016/j.ipm.2021.102844_b12 |
| SSID | ssj0004512 |
| Score | 2.6679401 |
| Snippet | Previous studies have adopted unsupervised machine learning with dimension reduction functions for cyberattack detection, which are limited to performing... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 102844 |
| SubjectTerms | Algorithms Anomalies Cyberattacks Cybercrime Data Deep autoencoder Density Domains Experiments GMM Machine learning Multidomain data Normal distribution Optimization Outliers (statistics) Probabilistic models Robustness Skewness |
| Title | Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection |
| URI | https://dx.doi.org/10.1016/j.ipm.2021.102844 https://www.proquest.com/docview/2641589598 |
| Volume | 59 |
| WOSCitedRecordID | wos000744117200003&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: 1873-5371 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004512 issn: 0306-4573 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELbQlgMXRHmIQot8QBxAqZLY3iTHVbW8Dr1QxIpL5Dg2zULdqEnQ9t93_MpGi6gAiUsURYkdeT6P5z0IvYQzTVHFiojTJI8opzKq0sKkPvEigfMtm_PaNpvITk_z1aoIHt3OthPItM43m6L9r6SGZ0Bskzr7F-QeB4UHcA9EhyuQHa5_RPil7uSFyYcadDe0hhV0IFTyob80NStN3LJ1GLzjQ2cTKC-ajfUi2J44NupQXFem1HLPxfc3textsJaeSrE-h8lCp3WZBs7iMPfRsNNwmoV2ccD-iLTGe8dgvp4318MWnaPt-uR80GsY-9vUJAHa7BiT5exkIVdmG5hk87PieUSZa1xyLB27zTMSMeKasAR-7CuEN1u1-Bc27ywO6-OmNcUE0sQUoMhdHcmd6tmfzLRmVlBtgX-Z03ovzViRz9De4sNy9XFSWj7xLif3m8EFboMBdyb6nRCzc5xbGeXsAbrvlQu8cKDYR3ekfoiOfGoKfoUndMOeqT9CXwJg8BQweAoYDIDBATDYAwZbwGAYEU8Ag0fAPEaf3y7PTt5Hvt1GJEjK-ijlVaIko8aioGgFqq6QPFY5VxKYfFxxUhMeJxUjsPFZLWpVE5Hyep4VPFVUkidopi-1fIpwnSlBMi4kCJMgISpOYikzDsp7BeNVyQGKw_qVwteiNy1RfpQh6HBdwpKXZslLt-QH6PX4SesKsdz2Mg1EKb0k6STEEhB022eHgYCl39FdCRpDwvICIPPs30Z9ju5tN8khmvVXgzxCd8XPvumuXngY3gB_daXV |
| 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=Ensemble+unsupervised+autoencoders+and+Gaussian+mixture+model+for+cyberattack+detection&rft.jtitle=Information+processing+%26+management&rft.au=An%2C+Peng&rft.au=Wang%2C+Zhiyuan&rft.au=Zhang%2C+Chunjiong&rft.date=2022-03-01&rft.pub=Elsevier+Ltd&rft.issn=0306-4573&rft.eissn=1873-5371&rft.volume=59&rft.issue=2&rft_id=info:doi/10.1016%2Fj.ipm.2021.102844&rft.externalDocID=S0306457321003162 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-4573&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-4573&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-4573&client=summon |