A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View
Machine learning is one of the most prevailing techniques in computer science, and it has been widely applied in image processing, natural language processing, pattern recognition, cybersecurity, and other fields. Regardless of successful applications of machine learning algorithms in many scenarios...
Saved in:
| Published in: | IEEE access Vol. 6; pp. 12103 - 12117 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Piscataway
IEEE
01.01.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 2169-3536, 2169-3536 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Machine learning is one of the most prevailing techniques in computer science, and it has been widely applied in image processing, natural language processing, pattern recognition, cybersecurity, and other fields. Regardless of successful applications of machine learning algorithms in many scenarios, e.g., facial recognition, malware detection, automatic driving, and intrusion detection, these algorithms and corresponding training data are vulnerable to a variety of security threats, inducing a significant performance decrease. Hence, it is vital to call for further attention regarding security threats and corresponding defensive techniques of machine learning, which motivates a comprehensive survey in this paper. Until now, researchers from academia and industry have found out many security threats against a variety of learning algorithms, including naive Bayes, logistic regression, decision tree, support vector machine (SVM), principle component analysis, clustering, and prevailing deep neural networks. Thus, we revisit existing security threats and give a systematic survey on them from two aspects, the training phase and the testing/inferring phase. After that, we categorize current defensive techniques of machine learning into four groups: security assessment mechanisms, countermeasures in the training phase, those in the testing or inferring phase, data security, and privacy. Finally, we provide five notable trends in the research on security threats and defensive techniques of machine learning, which are worth doing in-depth studies in future. |
|---|---|
| AbstractList | Machine learning is one of the most prevailing techniques in computer science, and it has been widely applied in image processing, natural language processing, pattern recognition, cybersecurity, and other fields. Regardless of successful applications of machine learning algorithms in many scenarios, e.g., facial recognition, malware detection, automatic driving, and intrusion detection, these algorithms and corresponding training data are vulnerable to a variety of security threats, inducing a significant performance decrease. Hence, it is vital to call for further attention regarding security threats and corresponding defensive techniques of machine learning, which motivates a comprehensive survey in this paper. Until now, researchers from academia and industry have found out many security threats against a variety of learning algorithms, including naive Bayes, logistic regression, decision tree, support vector machine (SVM), principle component analysis, clustering, and prevailing deep neural networks. Thus, we revisit existing security threats and give a systematic survey on them from two aspects, the training phase and the testing/inferring phase. After that, we categorize current defensive techniques of machine learning into four groups: security assessment mechanisms, countermeasures in the training phase, those in the testing or inferring phase, data security, and privacy. Finally, we provide five notable trends in the research on security threats and defensive techniques of machine learning, which are worth doing in-depth studies in future. |
| Author | Yu, Shui Leung, Victor C. M. Zhao, Wentao Liu, Qiang Li, Pan Cai, Wei |
| Author_xml | – sequence: 1 givenname: Qiang orcidid: 0000-0003-2922-3518 surname: Liu fullname: Liu, Qiang email: qiangliu06@nudt.edu.cn organization: College of Computer, National University of Defense Technology, Changsha, China – sequence: 2 givenname: Pan surname: Li fullname: Li, Pan organization: College of Computer, National University of Defense Technology, Changsha, China – sequence: 3 givenname: Wentao surname: Zhao fullname: Zhao, Wentao organization: College of Computer, National University of Defense Technology, Changsha, China – sequence: 4 givenname: Wei surname: Cai fullname: Cai, Wei organization: Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada – sequence: 5 givenname: Shui orcidid: 0000-0003-4485-6743 surname: Yu fullname: Yu, Shui organization: School of Information Technology, Deakin University Melbourne Burwood Campus, Burwood, VIC, Australia – sequence: 6 givenname: Victor C. M. surname: Leung fullname: Leung, Victor C. M. organization: Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada |
| BookMark | eNp9kUFrGzEQhUVJoWmaX5CLIGe7I-1qV-rN2EkbcOnBbm9FaKVRLONIqVZ28L_vupuWkEPnomF43-OJ956cxRSRkCsGU8ZAfZzN5zer1ZQDk1MuQTQS3pBzzho1qUTVnL3Y35HLvt_CMHI4ifac_JzR1T4f8EhTpCu0-xzKka43GU3pqYmOLtBj7MMB6RrtJoZfe-xp8vSrsZsQkS7R5Bji_Sc6owtTDF3kQRzpj4BPH8hbb3Y9Xj6_F-T77c16_mWy_Pb5bj5bTmwNskzQMq6kdS048EJB1TqGXHLRMWaUNNLYTiJ2TWu5a1rgtXW-Eg2qlje1xOqC3I2-LpmtfszhweSjTiboP4eU77XJJdgdauvBdt6pDoSva2iMUg5b0YKspa8BBq_r0esxp9Nfi96mfY5DfM1rIVQFCtSgUqPK5tT3Gb22oZgSUizZhJ1moE_l6LEcfSpHP5czsNUr9m_i_1NXIxUQ8R8h-ZCGi-o3jpObWg |
| CODEN | IAECCG |
| CitedBy_id | crossref_primary_10_1109_TKDE_2021_3117608 crossref_primary_10_1109_ACCESS_2020_2987435 crossref_primary_10_3389_fdata_2024_1381163 crossref_primary_10_32604_cmc_2022_019709 crossref_primary_10_1016_j_cose_2024_103988 crossref_primary_10_1186_s13673_019_0190_9 crossref_primary_10_1016_j_jisa_2022_103121 crossref_primary_10_1145_3542818 crossref_primary_10_1016_j_cose_2023_103627 crossref_primary_10_1109_ACCESS_2024_3395118 crossref_primary_10_1109_ACCESS_2020_3036074 crossref_primary_10_1145_3427376 crossref_primary_10_1016_j_cose_2021_102376 crossref_primary_10_1016_j_eswa_2021_115782 crossref_primary_10_1016_j_phycom_2023_102002 crossref_primary_10_1016_j_smhl_2021_100262 crossref_primary_10_1109_ACCESS_2020_2974752 crossref_primary_10_3390_computers8030059 crossref_primary_10_1007_s00521_022_07178_5 crossref_primary_10_1587_transinf_2019EDP7188 crossref_primary_10_1109_TSE_2020_3034721 crossref_primary_10_3390_jsan9030037 crossref_primary_10_1109_ACCESS_2021_3084841 crossref_primary_10_1109_ACCESS_2024_3519524 crossref_primary_10_1109_TNSE_2025_3528831 crossref_primary_10_1016_j_cose_2023_103297 crossref_primary_10_1145_3636551 crossref_primary_10_1007_s10207_024_00813_3 crossref_primary_10_1007_s10916_020_01646_y crossref_primary_10_1109_ACCESS_2019_2942390 crossref_primary_10_1007_s11036_019_01397_2 crossref_primary_10_1007_s10489_020_02086_4 crossref_primary_10_1145_3417987 crossref_primary_10_1145_3485133 crossref_primary_10_1145_3627536 crossref_primary_10_1016_j_future_2022_03_001 crossref_primary_10_1109_COMST_2024_3353265 crossref_primary_10_1109_MSEC_2019_2907097 crossref_primary_10_1145_3398394 crossref_primary_10_1002_sres_2865 crossref_primary_10_1109_ACCESS_2020_3011107 crossref_primary_10_3390_app11104471 crossref_primary_10_1109_ACCESS_2019_2894819 crossref_primary_10_1186_s13635_021_00124_3 crossref_primary_10_1109_ACCESS_2020_3029280 crossref_primary_10_1007_s11277_021_08284_8 crossref_primary_10_1002_ett_4085 crossref_primary_10_1109_TETCI_2020_2968933 crossref_primary_10_1108_ICS_10_2022_0165 crossref_primary_10_1007_s11036_019_01401_9 crossref_primary_10_1007_s10115_023_01906_6 crossref_primary_10_1145_3613244 crossref_primary_10_1007_s11042_023_16126_x crossref_primary_10_1109_ACCESS_2025_3547642 crossref_primary_10_3390_info14110600 crossref_primary_10_1002_ett_3947 crossref_primary_10_1016_j_fss_2018_11_004 crossref_primary_10_1177_1548512920951275 crossref_primary_10_1177_2053951720908892 crossref_primary_10_3390_s21124237 crossref_primary_10_1016_j_comcom_2023_12_015 crossref_primary_10_1016_j_epsr_2022_108975 crossref_primary_10_1109_ACCESS_2020_3033494 crossref_primary_10_1109_MNET_011_1900450 crossref_primary_10_3390_su13168885 crossref_primary_10_1002_ett_4011 crossref_primary_10_3390_app10020724 crossref_primary_10_1016_j_adhoc_2023_103385 crossref_primary_10_1007_s11623_021_1471_9 crossref_primary_10_3389_fdata_2020_00023 crossref_primary_10_1016_j_sysarc_2020_101940 crossref_primary_10_1109_ACCESS_2020_2969276 crossref_primary_10_57197_JDR_2024_0101 crossref_primary_10_1109_ACCESS_2019_2962525 crossref_primary_10_3390_s18061699 crossref_primary_10_1109_COMST_2023_3329027 crossref_primary_10_1016_j_jisa_2021_102949 crossref_primary_10_1016_j_iot_2021_100462 crossref_primary_10_1109_ACCESS_2020_3045078 crossref_primary_10_1016_j_cose_2024_103929 crossref_primary_10_1109_TNSE_2021_3055835 crossref_primary_10_4018_JOEUC_371412 crossref_primary_10_1016_j_comcom_2022_06_012 crossref_primary_10_3103_S0146411622080211 crossref_primary_10_1007_s40031_021_00563_z crossref_primary_10_1002_ett_4400 crossref_primary_10_1145_3628446 crossref_primary_10_4271_01_16_03_0019 crossref_primary_10_1002_asmb_70029 crossref_primary_10_3390_technologies11040107 crossref_primary_10_1016_j_ress_2024_110682 crossref_primary_10_1109_COMST_2022_3205184 crossref_primary_10_1145_3469659 crossref_primary_10_1007_s11036_019_01402_8 crossref_primary_10_1109_COMST_2023_3319492 crossref_primary_10_1145_3484491 crossref_primary_10_1109_TCE_2022_3232478 crossref_primary_10_1109_JIOT_2024_3349381 crossref_primary_10_1016_j_cose_2023_103268 crossref_primary_10_1109_ACCESS_2020_3018170 crossref_primary_10_1016_j_neucom_2020_07_126 crossref_primary_10_1109_TCCN_2022_3186331 crossref_primary_10_1051_e3sconf_202122901004 crossref_primary_10_1007_s11277_022_09960_z crossref_primary_10_1109_TII_2022_3197190 crossref_primary_10_1186_s42400_021_00092_8 crossref_primary_10_1109_ACCESS_2020_2996226 crossref_primary_10_1109_TCSS_2019_2960824 crossref_primary_10_1109_TNNLS_2019_2933524 crossref_primary_10_1016_j_cose_2020_102061 crossref_primary_10_1109_ACCESS_2019_2941021 crossref_primary_10_1002_cpe_6561 crossref_primary_10_1109_JIOT_2021_3126811 crossref_primary_10_1080_08982112_2024_2403606 crossref_primary_10_1007_s11036_019_01399_0 crossref_primary_10_1016_j_artmed_2023_102722 crossref_primary_10_1016_j_cose_2023_103250 crossref_primary_10_1109_ACCESS_2023_3306333 crossref_primary_10_1109_COMST_2020_2988293 crossref_primary_10_3390_ani10091690 crossref_primary_10_1145_3439729 crossref_primary_10_1109_ACCESS_2019_2908033 crossref_primary_10_1016_j_ress_2023_109299 crossref_primary_10_1016_j_ins_2020_03_036 crossref_primary_10_1016_j_compeleceng_2025_110146 crossref_primary_10_1109_JIOT_2022_3181990 crossref_primary_10_1088_1742_6596_2303_1_012008 crossref_primary_10_1016_j_heliyon_2024_e37571 crossref_primary_10_1007_s11036_019_01403_7 crossref_primary_10_1016_j_sysarc_2022_102644 crossref_primary_10_1016_j_comcom_2023_09_030 crossref_primary_10_1109_JLT_2018_2864676 crossref_primary_10_1145_3374217 crossref_primary_10_3390_jcp5030041 crossref_primary_10_1109_ACCESS_2018_2871131 crossref_primary_10_1109_ACCESS_2020_3041765 crossref_primary_10_1016_j_procs_2022_07_083 crossref_primary_10_1109_ACCESS_2021_3136889 crossref_primary_10_1109_COMST_2022_3171465 crossref_primary_10_1109_TCYB_2019_2940940 crossref_primary_10_1109_ACCESS_2020_3031966 crossref_primary_10_1145_3568020 crossref_primary_10_1109_ACCESS_2021_3058278 crossref_primary_10_1007_s11276_019_02125_0 crossref_primary_10_1016_j_cose_2024_103853 crossref_primary_10_1109_ACCESS_2021_3084545 crossref_primary_10_1109_ACCESS_2023_3294840 crossref_primary_10_3390_s22062194 crossref_primary_10_1109_MNET_011_2000245 crossref_primary_10_1016_j_comnet_2019_06_015 crossref_primary_10_1016_j_comnet_2021_107871 crossref_primary_10_1109_ACCESS_2021_3078265 crossref_primary_10_56294_dm2025739 crossref_primary_10_4102_sajbm_v56i1_4766 crossref_primary_10_1109_COMST_2023_3317242 crossref_primary_10_1007_s10462_023_10415_5 crossref_primary_10_1093_comjnl_bxae023 crossref_primary_10_1145_3436755 crossref_primary_10_1088_1757_899X_1022_1_012037 crossref_primary_10_1109_OJCOMS_2024_3356076 crossref_primary_10_3390_systems11040211 crossref_primary_10_1016_j_jisa_2025_104010 crossref_primary_10_1109_JIOT_2020_2991693 crossref_primary_10_1109_TMC_2024_3382776 crossref_primary_10_1145_3736753 crossref_primary_10_3390_electronics9091379 crossref_primary_10_1109_COMST_2020_2986444 |
| Cites_doi | 10.1109/ACCESS.2017.2696365 10.1145/1654988.1654990 10.1007/11787006_1 10.1016/j.bdr.2015.04.001 10.1109/ICB.2013.6613006 10.1145/1143844.1143889 10.1145/2909827.2930784 10.1109/EuroSP.2016.36 10.1007/s10994-010-5188-5 10.1145/2517312.2517321 10.1109/SP.2017.41 10.1109/ACCESS.2014.2325029 10.1007/978-3-642-21557-5_37 10.1109/SP.2014.20 10.1142/S0218001414600027 10.1145/2046684.2046692 10.1109/TKDE.2013.57 10.1145/1081870.1081950 10.1109/TDSC.2017.2700270 10.1145/1014052.1014066 10.1145/3133956.3134083 10.1109/TNNLS.2016.2593488 10.1109/ACCESS.2016.2577036 10.1109/SP.2016.41 10.24963/ijcai.2017/551 10.1007/978-3-642-34620-0_21 10.1007/978-3-642-40994-3_25 10.1109/SP.2017.49 10.1109/CVPR.2017.17 10.1145/2020408.2020495 10.1016/j.ins.2013.03.022 10.1145/1644893.1644895 10.1145/2810103.2813677 10.29012/jpc.v4i1.612 10.1109/TKDE.2014.2320725 10.1145/2976749.2978318 10.1109/TKDE.2016.2606428 10.1007/978-3-319-02300-7_4 10.1145/2666652.2666666 10.1109/CISDA.2007.368148 10.1007/s10994-017-5663-3 10.1145/1128817.1128824 10.1109/JBHI.2014.2344095 10.1016/j.neucom.2017.01.026 10.1007/s13042-010-0007-7 10.1109/CVPR.2016.282 10.1145/2976749.2978392 10.1016/j.patrec.2012.11.006 10.1007/978-0-387-88735-7_2 10.1007/978-3-642-34166-3_46 10.1109/ICME.2014.6890141 10.1016/j.neucom.2014.08.081 10.1109/CVPRW.2017.172 10.1109/TCYB.2015.2415032 10.14722/ndss.2016.23115 10.1007/978-3-662-44415-3_5 10.1145/2484313.2484327 10.1145/3052973.3053009 10.1007/978-0-387-39940-9_466 10.1109/CSF.2016.32 10.1145/1989323.1989345 10.1145/3041008.3041012 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA |
| DOI | 10.1109/ACCESS.2018.2805680 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Materials Research Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2169-3536 |
| EndPage | 12117 |
| ExternalDocumentID | oai_doaj_org_article_cf0cbfd9b05f4406a99de7570848f400 10_1109_ACCESS_2018_2805680 8290925 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61702539; 61728201 funderid: 10.13039/501100001809 |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D RIG |
| ID | FETCH-LOGICAL-c408t-ec1298cd70d0f59037d1e2825b11a98a8acb8eeb67c2d67024cdf356e972648e3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 250 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000428582200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2169-3536 |
| IngestDate | Fri Oct 03 12:50:37 EDT 2025 Sun Jun 29 15:41:45 EDT 2025 Tue Nov 18 21:24:07 EST 2025 Sat Nov 29 03:33:04 EST 2025 Wed Aug 27 02:51:58 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/OAPA.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c408t-ec1298cd70d0f59037d1e2825b11a98a8acb8eeb67c2d67024cdf356e972648e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-2922-3518 0000-0003-4485-6743 |
| OpenAccessLink | https://ieeexplore.ieee.org/document/8290925 |
| PQID | 2455930909 |
| PQPubID | 4845423 |
| PageCount | 15 |
| ParticipantIDs | crossref_citationtrail_10_1109_ACCESS_2018_2805680 ieee_primary_8290925 crossref_primary_10_1109_ACCESS_2018_2805680 proquest_journals_2455930909 doaj_primary_oai_doaj_org_article_cf0cbfd9b05f4406a99de7570848f400 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-01-01 |
| PublicationDateYYYYMMDD | 2018-01-01 |
| PublicationDate_xml | – month: 01 year: 2018 text: 2018-01-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE access |
| PublicationTitleAbbrev | Access |
| PublicationYear | 2018 |
| 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 | ref56 ref55 masha (ref59) 2016 dowlin (ref109) 2016 tramèr (ref71) 2016 ref51 ref50 wittel (ref6) 2004 grosse (ref96) 2017 ref48 brückner (ref86) 2012; 13 ref42 yang (ref45) 2017 ref44 mei (ref46) 2015 ref8 sengupta (ref97) 2017 ref9 ref4 li (ref36) 2016 ref3 xiao (ref47) 2015 ref5 ref100 ref40 kloft (ref41) 2012; 13 šrndi? (ref24) 2013 metzen (ref90) 2017 ref30 ref33 ref32 amodei (ref15) 2016 kusner (ref104) 2015 ref39 nguyen (ref31) 2015 ref38 bhagoji (ref95) 2017 hu (ref49) 2017 carlini (ref94) 2016 goodfellow (ref91) 2015 ref23 ref26 alfeld (ref37) 2016 ref25 ref20 ref22 mopuri (ref66) 2017 ref21 teo (ref84) 2007 rizzi (ref74) 2009 ref28 papernot (ref53) 2016 ref27 li (ref57) 2014 lowd (ref7) 2005 biggio (ref43) 2012 ref13 liu (ref34) 2017 ref12 ref14 ref19 ref18 kurakin (ref35) 2017 ref93 grosse (ref58) 2016 aslett (ref107) 2015 ref85 yao (ref108) 2017; 2 ref87 fredrikson (ref70) 2014 ref82 ref83 ref80 ref79 ref78 ref75 ref105 ref77 ref102 ref76 ref103 ref2 ref1 damgård (ref106) 2012 carlini (ref11) 2016 ref111 ref73 ref72 ref110 abbasi (ref99) 2017 ref68 laishram (ref81) 2016 ref67 ref69 ref64 papernot (ref10) 2016 rosenberg (ref54) 2017 ref63 qiu (ref17) 2016; 2016 ref65 gu (ref92) 2015 pihur (ref101) 2014 szegedy (ref29) 2014 tramèr (ref52) 2017 feinman (ref89) 2017 xu (ref88) 2017 ref60 ref62 tramèr (ref98) 2018 ref61 papernot (ref16) 2016 |
| References_xml | – ident: ref5 doi: 10.1109/ACCESS.2017.2696365 – ident: ref75 doi: 10.1145/1654988.1654990 – year: 2015 ident: ref92 publication-title: Towards deep neural network architectures robust to adversarial examples – ident: ref100 doi: 10.1007/11787006_1 – ident: ref3 doi: 10.1016/j.bdr.2015.04.001 – ident: ref9 doi: 10.1109/ICB.2013.6613006 – ident: ref83 doi: 10.1145/1143844.1143889 – start-page: 601 year: 2016 ident: ref71 article-title: Stealing machine learning models via prediction APIs publication-title: Proc 25th Usenix Security Symp – ident: ref21 doi: 10.1145/2909827.2930784 – ident: ref33 doi: 10.1109/EuroSP.2016.36 – start-page: 17 year: 2014 ident: ref70 article-title: Privacy in pharmacogenetics: An end-to-end case study of personalized warfarin dosing publication-title: Proc Usenix Secur Symp – ident: ref18 doi: 10.1007/s10994-010-5188-5 – start-page: 1 year: 2004 ident: ref6 article-title: On attacking statistical spam filters publication-title: Proc 1st Conf Email and Anti-Spam – ident: ref28 doi: 10.1145/2517312.2517321 – ident: ref68 doi: 10.1109/SP.2017.41 – year: 2017 ident: ref49 publication-title: Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN – ident: ref4 doi: 10.1109/ACCESS.2014.2325029 – start-page: 1489 year: 2007 ident: ref84 article-title: Convex learning with invariances publication-title: Proc 20th Int Conf Neural Inf Process Syst (NIPS) – year: 2016 ident: ref10 publication-title: Practical black-box attacks against machine learning – ident: ref79 doi: 10.1007/978-3-642-21557-5_37 – year: 2016 ident: ref15 publication-title: Concrete problems in ai safety – ident: ref63 doi: 10.1109/SP.2014.20 – year: 2014 ident: ref29 publication-title: Intriguing properties of neural networks – ident: ref39 doi: 10.1142/S0218001414600027 – start-page: 2087 year: 2014 ident: ref57 article-title: Feature cross-substitution in adversarial classification publication-title: Proc 27th Int Conf Neural Inf Process Syst (NIPS) – year: 2017 ident: ref90 publication-title: On detecting adversarial perturbations – ident: ref76 doi: 10.1145/2046684.2046692 – start-page: 681 year: 2015 ident: ref46 article-title: The security of latent Dirichlet allocation publication-title: Proc Int Conf Artif Intell Statist – ident: ref19 doi: 10.1109/TKDE.2013.57 – year: 2017 ident: ref89 publication-title: Detecting adversarial samples from artifacts – ident: ref13 doi: 10.1145/1081870.1081950 – ident: ref82 doi: 10.1109/TDSC.2017.2700270 – ident: ref12 doi: 10.1145/1014052.1014066 – year: 2017 ident: ref35 publication-title: Adversarial examples in the physical world – ident: ref42 doi: 10.1145/3133956.3134083 – start-page: 1689 year: 2015 ident: ref47 article-title: Is feature selection secure against training data poisoning? publication-title: Proc Int Conf Int Conf Mach Learn (ICML) – year: 2017 ident: ref96 publication-title: On the (statistical) detection of adversarial examples – start-page: 201 year: 2016 ident: ref109 article-title: CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy publication-title: Proc 33rd Int Conf Mach Learn – volume: 2016 year: 2016 ident: ref17 article-title: A survey of machine learning for big data processing publication-title: EURASIP J Adv Signal Process – year: 2017 ident: ref34 publication-title: Delving into transferable adversarial examples and black-box attacks – ident: ref87 doi: 10.1109/TNNLS.2016.2593488 – ident: ref2 doi: 10.1109/ACCESS.2016.2577036 – start-page: 1467 year: 2012 ident: ref43 article-title: Poisoning attacks against support vector machines publication-title: Proc 29th Int Conf Int Conf Mach Learn (ICML) – ident: ref93 doi: 10.1109/SP.2016.41 – start-page: 513 year: 2016 ident: ref11 article-title: Hidden voice commands publication-title: Proc 25th Usenix Security Symp – year: 2016 ident: ref58 publication-title: Adversarial perturbations against deep neural networks for malware classification – ident: ref50 doi: 10.24963/ijcai.2017/551 – year: 2017 ident: ref95 publication-title: Enhancing robustness of machine learning systems via data transformations – start-page: 427 year: 2015 ident: ref31 article-title: Deep neural networks are easily fooled: High confidence predictions for unrecognizable images publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) – ident: ref27 doi: 10.1007/978-3-642-34620-0_21 – ident: ref55 doi: 10.1007/978-3-642-40994-3_25 – year: 2017 ident: ref88 publication-title: Feature squeezing Detecting adversarial examples in deep neural networks – year: 2016 ident: ref53 publication-title: Transferability in machine learning from phenomena to black-box attacks using adversarial samples – year: 2018 ident: ref98 publication-title: Ensemble adversarial training Attacks and defenses – ident: ref65 doi: 10.1109/SP.2017.49 – year: 2016 ident: ref59 publication-title: Adversarial Attacks on Image Recognition – ident: ref67 doi: 10.1109/CVPR.2017.17 – ident: ref85 doi: 10.1145/2020408.2020495 – ident: ref22 doi: 10.1016/j.ins.2013.03.022 – ident: ref77 doi: 10.1145/1644893.1644895 – ident: ref20 doi: 10.1145/2810103.2813677 – ident: ref102 doi: 10.29012/jpc.v4i1.612 – ident: ref23 doi: 10.1109/TKDE.2014.2320725 – ident: ref103 doi: 10.1145/2976749.2978318 – start-page: 1885 year: 2016 ident: ref36 article-title: Data poisoning attacks on factorization-based collaborative filtering publication-title: Proc Adv Neural Inf Process Syst – ident: ref110 doi: 10.1109/TKDE.2016.2606428 – year: 2016 ident: ref94 publication-title: Defensive distillation is not robust to adversarial examples – year: 2017 ident: ref45 publication-title: Generative poisoning attack method against neural networks – ident: ref73 doi: 10.1007/978-3-319-02300-7_4 – year: 2017 ident: ref66 publication-title: Fast feature fool A data independent approach to universal adversarial perturbations – ident: ref26 doi: 10.1145/2666652.2666666 – start-page: 1 year: 2013 ident: ref24 article-title: Detection of malicious PDF files based on hierarchical document structure publication-title: Proc 20th Annu Netw Distrib Syst Security Symp – volume: 2 start-page: 81 year: 2017 ident: ref108 article-title: Investigation on distributed K-means clustering algorithm of homomorphic encryption publication-title: Computer Technology and Development – year: 2016 ident: ref81 publication-title: Curie A method for protecting SVM classifier from poisoning attack – ident: ref62 doi: 10.1109/CISDA.2007.368148 – year: 2017 ident: ref97 publication-title: MTDeep Boosting the security of deep neural nets against adversarial attacks with moving target defense – year: 2016 ident: ref16 publication-title: Towards the science of security and privacy in machine learning – year: 2017 ident: ref99 publication-title: Robustness to adversarial examples through an ensemble of specialists – ident: ref72 doi: 10.1007/s10994-017-5663-3 – ident: ref14 doi: 10.1145/1128817.1128824 – volume: 13 start-page: 3681 year: 2012 ident: ref41 article-title: Security analysis of online centroid anomaly detection publication-title: J Mach Learn Res – start-page: 1 year: 2005 ident: ref7 article-title: Good word attacks on statistical spam filters publication-title: Proc 2nd Conf Email Anti-Spam – ident: ref48 doi: 10.1109/JBHI.2014.2344095 – ident: ref1 doi: 10.1016/j.neucom.2017.01.026 – start-page: 1452 year: 2016 ident: ref37 article-title: Data poisoning attacks against autoregressive models publication-title: Proc AAAI Conf Artif Intell (AAAI) – ident: ref78 doi: 10.1007/s13042-010-0007-7 – ident: ref32 doi: 10.1109/CVPR.2016.282 – start-page: 918 year: 2015 ident: ref104 article-title: Differentially private Bayesian optimization publication-title: Proc Int Conf Mach Learn (ICML) – volume: 13 start-page: 2617 year: 2012 ident: ref86 article-title: Static prediction games for adversarial learning problems publication-title: J Mach Learn Res – year: 2017 ident: ref52 publication-title: The space of transferable adversarial examples – ident: ref8 doi: 10.1145/2976749.2978392 – ident: ref40 doi: 10.1016/j.patrec.2012.11.006 – ident: ref80 doi: 10.1007/978-0-387-88735-7_2 – ident: ref38 doi: 10.1007/978-3-642-34166-3_46 – start-page: 643 year: 2012 ident: ref106 article-title: Multiparty Computation from Somewhat Homomorphic Encryption publication-title: Proc 32nd Annu Cryptol Conf Adv Cryptol (CRYPTO) – ident: ref105 doi: 10.1109/ICME.2014.6890141 – year: 2015 ident: ref91 publication-title: Explaining and Harnessing Adversarial Examples – ident: ref51 doi: 10.1016/j.neucom.2014.08.081 – ident: ref30 doi: 10.1109/CVPRW.2017.172 – start-page: 1054 year: 2014 ident: ref101 article-title: RAPPOR: Randomized aggregatable privacy-preserving ordinal response publication-title: Proc ACM SIGSAC Conf Comput Commun Secur – year: 2015 ident: ref107 publication-title: Encrypted statistical machine learning New privacy preserving methods – ident: ref56 doi: 10.1109/TCYB.2015.2415032 – ident: ref61 doi: 10.14722/ndss.2016.23115 – year: 2017 ident: ref54 publication-title: Generic black-box end-to-end attack against state of the art API call based malware classifiers – ident: ref25 doi: 10.1007/978-3-662-44415-3_5 – ident: ref60 doi: 10.1145/2484313.2484327 – ident: ref64 doi: 10.1145/3052973.3053009 – start-page: 3525 year: 2009 ident: ref74 article-title: What-if analysis publication-title: Encyclopedia of Database Systems doi: 10.1007/978-0-387-39940-9_466 – ident: ref69 doi: 10.1109/CSF.2016.32 – ident: ref111 doi: 10.1145/1989323.1989345 – ident: ref44 doi: 10.1145/3041008.3041012 |
| SSID | ssj0000816957 |
| Score | 2.5906048 |
| SecondaryResourceType | review_article |
| Snippet | Machine learning is one of the most prevailing techniques in computer science, and it has been widely applied in image processing, natural language processing,... |
| SourceID | doaj proquest crossref ieee |
| SourceType | Open Website Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 12103 |
| SubjectTerms | adversarial samples Algorithms Artificial neural networks Clustering Cybersecurity Decision analysis Decision trees defensive techniques Face recognition Image processing Machine learning Machine learning algorithms Malware Natural language processing Object recognition Pattern recognition Principal components analysis Regression analysis Security security threats Support vector machines Taxonomy Testing Training Training data |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT8MwDI4Q4gAHxFMMBsqBI4X0mZjb2EAcACExEBcUpYkDSKhD2xji35O02TQJCS5cK6dtbNef3bqfCTl0xVpuUECUF5hGGag4UgKcQVJTZCXjltmaZ_aK39yIx0e4nRv15XvCGnrgRnEn2jJdWgMly23m0EcBGOQ59zzw1jmgj76Mw1wxVcdgEReQ80AzFDM46XS7bke-l0scJ8LBvieCnIOimrE_jFj5EZdrsLlYI6shS6Sd5u7WyQJWG2Rljjtwkzx16N3HcIJfdFDRuzCFjvZffBI4oqoytIe26U6n_SlR64gOLL2u-yeRBmrV51PaoT01VrQ39KGPPrzi5xa5vzjvdy-jMCsh0hkT4wi1A26hDWeG2RxYyk2M_r_UMo4VCCWULgViWXCdmII7ZNbGps5AwH2PG6bbZLEaVLhDqC5yAOQILlPJjFuKOlHKoksO0BWQRYskU7VJHYjE_TyLN1kXFAxko2vpdS2DrlvkaLboveHR-F38zNtjJupJsOsDzjVkcA35l2u0yKa35uwk_psxJHmLtKfWleGBHckkc6VVypzA7n9ceo8s--0072raZHE8_MB9sqQn49fR8KD21W-BMOlA priority: 102 providerName: Directory of Open Access Journals |
| Title | A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View |
| URI | https://ieeexplore.ieee.org/document/8290925 https://www.proquest.com/docview/2455930909 https://doaj.org/article/cf0cbfd9b05f4406a99de7570848f400 |
| Volume | 6 |
| WOSCitedRecordID | wos000428582200001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6S0EN76Cst3TYNOvQYJ_JTUm_b3YQemlDItuRShCyNkkDwln2k9JLfnpGsNYGWQi_GGI2R_UmaGWnmG4AP5KzVDqXK6gbLrFImz4xUBEjpmqrlwnMfeWa_iLMzeXGhvm7BwZALg4gx-AwPw208y3dzuw5bZUfh0E8V9TZsC9H0uVrDfkooIKFqkYiFcq6OxpMJfUOI3pKHhSRFH6gfHyifyNGfiqr8sRJH9XLy7P869hyeJjOSjXvcX8AWdi_hyQNywV34MWbn68Ut_mbzjp2nMnVsdhWsxCUznWNT9H34OpttmFyXbO7ZaQywRJa4Vy8_sjGbmpVh00VYG9n3a_z1Cr6dHM8mn7NUTCGzFZerDC1pdmmd4I77WvFSuBxD4mqb50ZJI41tJWLbCFu4RpDqts6XhKASIQgOy9ew0807fAPMNrVSKFCRKVM5EkVbGOORrAckD7MZQbH5y9ompvFQ8OJGR4-DK91DowM0OkEzgoNB6GdPtPHv5p8CfEPTwJIdHxAuOk06bT23rXeq5bWvyHIxSjkUtQg1BDwtXiPYDVgOL0kwjmBvMxh0mtFLXVTke5WcGrz9u9Q7eBw62G_P7MHOarHG9_DI3q6ul4v96OvT9fTueD8O3Hs7puhd |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1baxQxFD7UKtg-eKvF1ap58LHTZi6ZJL6tu5aK20XoKn2RkElObKHMyl5a_PcmmexQUATfhiEZMvmSc0nO-Q7AO--sMYtCZqzGMqukzjMtpAektHXVUO6oizyzEz6diosL-WULDvtcGESMwWd4FB7jXb6dm3U4KjsOl36yYPfgPquqgnbZWv2JSighIRlP1EI5lcfD0cj_RYjfEkeF8Ko-kD_eUT-RpT-VVflDFkcFc_L4_4b2BB4lQ5IMO-Sfwha2z2D3Dr3gHnwfkvP14gZ_kXlLzlOhOjK7DHbikujWkjG6LoCdzDZcrksyd-QshlgiSeyrP96TIRnrlSbjRZCO5NsV3j6HrycfZ6PTLJVTyExFxSpD43W7MJZTSx2TtOQ2x5C62uS5lkILbRqB2NTcFLbmXnkb60qPoeQhDA7Lfdhu5y2-AGJqJiVylN6YqazviqbQ2qG3H9D7mPUAis0sK5O4xkPJi2sVfQ4qVQeNCtCoBM0ADvtOPzuqjX83_xDg65sGnuz4wuOi0rZTxlHTOCsbylzlbRctpUXOeKgi4Lz4GsBewLL_SIJxAAebxaDSnl6qovLeV0l9g5d_7_UWHp7OziZq8mn6-RXshMF2hzUHsL1arPE1PDA3q6vl4k1cuL8Bgq_pfg |
| 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=A+Survey+on+Security+Threats+and+Defensive+Techniques+of+Machine+Learning%3A+A+Data+Driven+View&rft.jtitle=IEEE+access&rft.au=Liu%2C+Qiang&rft.au=Li%2C+Pan&rft.au=Zhao%2C+Wentao&rft.au=Cai%2C+Wei&rft.date=2018-01-01&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=6&rft.spage=12103&rft.epage=12117&rft_id=info:doi/10.1109%2FACCESS.2018.2805680&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2018_2805680 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon |