Machine Unlearning: Solutions and Challenges
Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged as a critical technique to selectively remove specific train...
Saved in:
| Published in: | IEEE transactions on emerging topics in computational intelligence Vol. 8; no. 3; pp. 2150 - 2168 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Piscataway
IEEE
01.06.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 2471-285X, 2471-285X |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged as a critical technique to selectively remove specific training data points' influence on trained models. This paper provides a comprehensive taxonomy and analysis of the solutions in machine unlearning. We categorize existing solutions into exact unlearning approaches that remove data influence thoroughly and approximate unlearning approaches that efficiently minimize data influence. By comprehensively reviewing solutions, we identify and discuss their strengths and limitations. Furthermore, we propose future directions to advance machine unlearning and establish it as an essential capability for trustworthy and adaptive machine learning models. This paper provides researchers with a roadmap of open problems, encouraging impactful contributions to address real-world needs for selective data removal. |
|---|---|
| AbstractList | Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged as a critical technique to selectively remove specific training data points' influence on trained models. This paper provides a comprehensive taxonomy and analysis of the solutions in machine unlearning. We categorize existing solutions into exact unlearning approaches that remove data influence thoroughly and approximate unlearning approaches that efficiently minimize data influence. By comprehensively reviewing solutions, we identify and discuss their strengths and limitations. Furthermore, we propose future directions to advance machine unlearning and establish it as an essential capability for trustworthy and adaptive machine learning models. This paper provides researchers with a roadmap of open problems, encouraging impactful contributions to address real-world needs for selective data removal. |
| Author | Jia, Xiaohua Xu, Jie Wang, Cong Wu, Zihan |
| Author_xml | – sequence: 1 givenname: Jie orcidid: 0000-0002-9924-4157 surname: Xu fullname: Xu, Jie email: jiexu49-c@my.cityu.edu.hk organization: Department of Computer Science, City University of Hong Kong, Hong Kong, Hong Kong – sequence: 2 givenname: Zihan orcidid: 0000-0002-6551-6177 surname: Wu fullname: Wu, Zihan organization: Department of Electrical Engineering, City University of Hong Kong, Hong Kong, Hong Kong – sequence: 3 givenname: Cong orcidid: 0000-0003-0547-315X surname: Wang fullname: Wang, Cong organization: Department of Computer Science, City University of Hong Kong, Hong Kong, Hong Kong – sequence: 4 givenname: Xiaohua orcidid: 0000-0001-8702-8302 surname: Jia fullname: Jia, Xiaohua organization: Department of Computer Science, City University of Hong Kong, Hong Kong, Hong Kong |
| BookMark | eNp9kE1PAjEQhhuDiYj8AeNhE68u9tO23gzxgwTjQUi8NaWdwpK1i-1y8N-7CAfiwdPM4X3mzTznqBebCAhdEjwiBOvb2eNsPBlRTPmIMakpxyeoT7kkJVXio3e0n6FhzmuMMdWCMMH76ObVulUVoZjHGmyKVVzeF-9NvW2rJubCRl-MV7auIS4hX6DTYOsMw8McoPlT1_1STt-eJ-OHaekYx23JgxKgFsETCNpSKaW3juIQHPGceRkUZdxpDhYI1wvGuQ8gglBSE-wpZgN0vb-7Sc3XFnJr1s02xa7SMCy0oIxI2qXoPuVSk3OCYDap-rTp2xBsdmLMrxizE2MOYjpI_YFc1drds22yVf0_erVHKwA46uJKqTvOfgC-SXHo |
| CODEN | ITETCU |
| CitedBy_id | crossref_primary_10_1016_j_ijepes_2025_110929 crossref_primary_10_1145_3749987 crossref_primary_10_1109_ACCESS_2025_3603866 crossref_primary_10_1109_JIOT_2024_3481213 crossref_primary_10_3390_ai6060108 crossref_primary_10_1145_3679014 crossref_primary_10_1007_s11227_025_07478_2 crossref_primary_10_23919_cje_2024_00_219 crossref_primary_10_3390_app15020647 crossref_primary_10_1109_TNNLS_2025_3530988 crossref_primary_10_1016_j_imavis_2025_105489 crossref_primary_10_1109_OJCS_2025_3543483 crossref_primary_10_1007_s10115_024_02312_2 crossref_primary_10_1080_02564602_2025_2522083 crossref_primary_10_1016_j_jisa_2025_104010 crossref_primary_10_1109_JIOT_2025_3583362 crossref_primary_10_1109_TCE_2025_3571956 crossref_primary_10_1080_14778238_2024_2420816 |
| Cites_doi | 10.1109/TDSC.2022.3194884 10.1109/TPAMI.2022.3229593 10.1109/INFOCOM53939.2023.10229075 10.1145/3460120.3484756 10.1002/j.1538-7305.1948.tb01338.x 10.1016/j.tics.2013.01.001 10.1007/978-3-030-58526-6_23 10.1007/s10462-009-9124-7 10.1109/SP46215.2023.10179336 10.1109/TMM.2017.2751969 10.1201/b12207 10.1109/INFOCOM48880.2022.9796721 10.1145/3548606.3559352 10.1109/tnnls.2023.3266233 10.2118/18761-MS 10.1145/3374664.3375751 10.1609/aimag.v29i3.2157 10.1109/CVPR42600.2020.01009 10.5555/3045118.3045167 10.1109/CVPR52688.2022.01017 10.56553/popets-2022-0072 10.1609/aaai.v36i8.20846 10.1007/978-3-319-57959-7 10.1145/3535101 10.1109/tdsc.2024.3382321 10.1023/A:1022859003006 10.1109/BigData47090.2019.9006179 10.1145/2523813 10.1007/11787006_1 10.1109/CVPR52729.2023.00750 10.1145/3485447.3511997 10.1145/3488932.3517406 10.1145/3603620 10.1145/3543507.3583547 10.1080/01621459.1974.10482962 10.1109/INFOCOM48880.2022.9796974 10.1109/SP46214.2022.9833596 10.1016/j.clsr.2017.08.007 10.24963/ijcai.2022/556 10.1109/EuroSP53844.2022.00027 10.1007/BF01582063 10.1109/5.726791 10.1109/CVPR52729.2023.01929 10.1109/CVPR46437.2021.00085 10.1145/3543507.3583521 10.1109/CVPR.2009.5206848 10.1145/3448016.3457239 10.1109/SP40001.2021.00106 10.14778/2824032.2824067 10.1109/TIFS.2024.3358993 10.1109/SP40001.2021.00019 10.24963/ijcai.2021/137 10.1109/SP.2015.35 10.1109/CVPR42600.2020.00932 10.1109/mc.2023.3333319 10.1145/3543507.3583305 10.1109/EuroSP51992.2021.00028 10.1007/978-3-031-20083-0_6 10.1007/978-3-030-45724-2_13 10.1016/j.inffus.2019.12.012 10.1126/science.aaa8685 10.4324/9781003106715-8 10.1145/276675.276685 10.1145/3485447.3512222 10.1109/TIFS.2023.3265506 10.1126/science.aaa8415 10.1145/3319535.3354208 10.1145/3196494.3196517 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| DBID | 97E RIA RIE AAYXX CITATION 7SP 8FD L7M |
| DOI | 10.1109/TETCI.2024.3379240 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2471-285X |
| EndPage | 2168 |
| ExternalDocumentID | 10_1109_TETCI_2024_3379240 10488864 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Hong Kong Research Grants Council grantid: CityU 11211422; R1012-21; R6021-20F; RFS2122-1S04; C2004-21G; C1029-22G |
| GroupedDBID | 0R~ 97E AAJGR AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE JAVBF OCL RIA RIE AAYXX CITATION 7SP 8FD L7M |
| ID | FETCH-LOGICAL-c340t-4f85e8bfd1ef9a2777dac20ffc1d43d7f8234c94eae149b344dfe5f587910d203 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 37 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001201941100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2471-285X |
| IngestDate | Sun Nov 30 05:23:12 EST 2025 Sat Nov 29 05:12:10 EST 2025 Tue Nov 18 22:18:17 EST 2025 Wed Aug 27 02:05:13 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c340t-4f85e8bfd1ef9a2777dac20ffc1d43d7f8234c94eae149b344dfe5f587910d203 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-6551-6177 0000-0002-9924-4157 0000-0003-0547-315X 0000-0001-8702-8302 |
| OpenAccessLink | https://scholars.cityu.edu.hk/en/publications/machine-unlearning-solutions-and-challenges |
| PQID | 3059523172 |
| PQPubID | 4437216 |
| PageCount | 19 |
| ParticipantIDs | ieee_primary_10488864 crossref_primary_10_1109_TETCI_2024_3379240 proquest_journals_3059523172 crossref_citationtrail_10_1109_TETCI_2024_3379240 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-06-01 |
| PublicationDateYYYYMMDD | 2024-06-01 |
| PublicationDate_xml | – month: 06 year: 2024 text: 2024-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE transactions on emerging topics in computational intelligence |
| PublicationTitleAbbrev | TETCI |
| PublicationYear | 2024 |
| 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 ref59 ref53 ref52 (ref10) 2023 Ngiam (ref105) 2011 Doshi-Velez (ref19) 2017 Mirzasoleiman (ref32) 2017 ref45 ref48 Biggio (ref13) 2012 ref47 ref41 ref44 Koh (ref21) 2017 ref8 ref7 Thudi (ref17) 2022 ref4 ref3 ref6 Shaik (ref57) 2023 ref100 Jia (ref39) 2021 ref101 ref35 ref34 ref36 ref30 Wang (ref84) 2023 ref38 Jagielski (ref108) 2020 Guo (ref43) 2020 Tishby (ref114) 2000 ref24 ref23 ref26 ref25 ref20 ref22 Shan (ref31) 2022 ref28 ref27 ref29 Merity (ref50) 2017 Izzo (ref90) 2021 Suriyakumar (ref65) 2022 Molnar (ref115) 2020 Voigt (ref9) 2017 Jayaraman (ref109) 2019 ref12 ref15 Cheng (ref82) 2022 Wu (ref40) 2020 ref97 Nguyen (ref55) 2022 ref96 ref11 ref98 Bojchevski (ref54) 2018 Ginart (ref61) 2019 ref16 ref18 Gokaslan (ref51) 2019 ref93 ref94 ref91 Serra (ref33) 2018 Carlini (ref37) 2022 ref89 ref86 ref85 ref88 ref87 Martens (ref71) 2020; 21 Neel (ref76) 2021 Nguyen (ref95) 2020 Maas (ref49) 2011 Mercuri (ref42) 2022 ref81 ref80 Sekhari (ref64) 2021 ref78 Lundberg (ref103) 2017 ref106 ref75 Chien (ref83) 2022 ref104 ref74 ref77 ref102 Steinhardt (ref14) 2017 Warnecke (ref70) 2023 ref2 Shumailov (ref99) 2021 ref1 Fu (ref5) 2021 Lu (ref92) 2022 ref111 ref73 ref72 ref110 Krizhevsky (ref46) 2009 Tanno (ref68) 2022 ref67 ref63 ref66 ref113 Gupta (ref107) 2021 McMahan (ref79) 2017 Brophy (ref58) 2021 ref60 Eisenhofer (ref112) 2022 ref62 Chaudhuri (ref69) 2011; 12 |
| References_xml | – start-page: 1092 volume-title: Proc. Int. Conf. Mach. Learn. year: 2021 ident: ref58 article-title: Machine unlearning for random forests – year: 2022 ident: ref42 article-title: An introduction to machine unlearning – start-page: 1 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2019 ident: ref61 article-title: Making AI forget you: Data deletion in machine learning – ident: ref93 doi: 10.1109/TDSC.2022.3194884 – start-page: 22205 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref108 article-title: Auditing differentially private machine learning: How private is private SGD? – ident: ref7 doi: 10.1109/TPAMI.2022.3229593 – start-page: 3575 volume-title: Proc. 31st USENIX Secur. Symp. year: 2022 ident: ref31 article-title: Poison forensics: Traceback of data poisoning attacks in neural networks – ident: ref62 doi: 10.1109/INFOCOM53939.2023.10229075 – start-page: 142 volume-title: Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol. year: 2011 ident: ref49 article-title: Learning word vectors for sentiment analysis – start-page: 1807 volume-title: Proc. 29th Int. Conf. Mach. Learn. year: 2012 ident: ref13 article-title: Poisoning attacks against support vector machines – start-page: 1 volume-title: Proc. 30th Annu. Netw. Distrib. System Secur. Symp. year: 2023 ident: ref70 article-title: Machine unlearning of features and labels – start-page: 931 volume-title: Proc. Algorithmic Learn. Theory year: 2021 ident: ref76 article-title: Descent-to-delete: Gradient-based methods for machine unlearning – ident: ref26 doi: 10.1145/3460120.3484756 – ident: ref111 doi: 10.1002/j.1538-7305.1948.tb01338.x – start-page: 1 volume-title: Proc. 6th In. Conf. Learn. Representations year: 2018 ident: ref54 article-title: Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking – ident: ref88 doi: 10.1016/j.tics.2013.01.001 – start-page: 4768 volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst. year: 2017 ident: ref103 article-title: A unified approach to interpreting model predictions – ident: ref72 doi: 10.1007/978-3-030-58526-6_23 – start-page: 1273 volume-title: Proc. Artif. Intell. Statist. year: 2017 ident: ref79 article-title: Communication-efficient learning of deep networks from decentralized data – ident: ref25 doi: 10.1007/s10462-009-9124-7 – ident: ref75 doi: 10.1109/SP46215.2023.10179336 – start-page: 3205 volume-title: Proc. 32nd USENIX Conf. Secur. Symp. year: 2023 ident: ref84 article-title: Inductive graph unlearning – year: 2023 ident: ref57 article-title: Exploring the landscape of machine unlearning: A survey and taxonomy – ident: ref104 doi: 10.1109/TMM.2017.2751969 – start-page: 1 year: 2009 ident: ref46 article-title: Learning multiple layers of features from tiny images – start-page: 2008 volume-title: Proc. Int. Conf. Artif. Intell. Statist. year: 2021 ident: ref90 article-title: Approximate data deletion from machine learning models – ident: ref23 doi: 10.1201/b12207 – start-page: 1895 volume-title: Proc. 28th USENIX Secur. Symp. year: 2019 ident: ref109 article-title: Evaluating differentially private machine learning in practice – ident: ref63 doi: 10.1109/INFOCOM48880.2022.9796721 – ident: ref59 doi: 10.1145/3548606.3559352 – ident: ref6 doi: 10.1109/tnnls.2023.3266233 – ident: ref47 doi: 10.2118/18761-MS – ident: ref80 doi: 10.1145/3374664.3375751 – volume: 21 start-page: 5776 issue: 1 year: 2020 ident: ref71 article-title: New insights and perspectives on the natural gradient method publication-title: J. Mach. Learn. Res. – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref5 article-title: Knowledge removal in sampling-based Bayesian inference – start-page: 16025 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref95 article-title: Variational Bayesian unlearning – ident: ref52 doi: 10.1609/aimag.v29i3.2157 – ident: ref1 doi: 10.1109/CVPR42600.2020.01009 – start-page: 1 volume-title: Proc. 11th Int. Conf. Learn. Representations year: 2022 ident: ref82 article-title: GNNDelete: A general strategy for unlearning in graph neural networks – start-page: 18075 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref64 article-title: Remember what you want to forget: Algorithms for machine unlearning – ident: ref106 doi: 10.5555/3045118.3045167 – start-page: 10355 volume-title: Proc. Int. Conf. Mach. Learn. year: 2020 ident: ref40 article-title: Deltagrad: Rapid retraining of machine learning models – ident: ref66 doi: 10.1109/CVPR52688.2022.01017 – ident: ref101 doi: 10.56553/popets-2022-0072 – start-page: 16319 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref107 article-title: Adaptive machine unlearning – ident: ref67 doi: 10.1609/aaai.v36i8.20846 – volume-title: The EU General Data Protection Regulation (GDPR). A Practical Guide year: 2017 ident: ref9 doi: 10.1007/978-3-319-57959-7 – year: 2022 ident: ref112 article-title: Verifiable and provably secure machine unlearning – ident: ref3 doi: 10.1145/3535101 – ident: ref100 doi: 10.1109/tdsc.2024.3382321 – start-page: 18021 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref99 article-title: Manipulating SGD with data ordering attacks – year: 2017 ident: ref19 article-title: Towards a rigorous science of interpretable machine learning – ident: ref24 doi: 10.1023/A:1022859003006 – ident: ref11 doi: 10.1109/BigData47090.2019.9006179 – ident: ref15 doi: 10.1145/2523813 – ident: ref44 doi: 10.1007/11787006_1 – ident: ref91 doi: 10.1109/CVPR52729.2023.00750 – ident: ref60 doi: 10.1145/3485447.3511997 – ident: ref94 doi: 10.1145/3488932.3517406 – ident: ref8 doi: 10.1145/3603620 – start-page: 2449 volume-title: Proc. 34th Int. Conf. Mach. Learn. year: 2017 ident: ref32 article-title: Deletion-robust submodular maximization: Data summarization with the right to be forgotten – ident: ref85 doi: 10.1145/3543507.3583547 – ident: ref22 doi: 10.1080/01621459.1974.10482962 – year: 2000 ident: ref114 article-title: The information bottleneck method – year: 2019 ident: ref51 article-title: Openwebtext corpus – ident: ref77 doi: 10.1109/INFOCOM48880.2022.9796974 – start-page: 27591 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2022 ident: ref92 article-title: QUARK: Controllable text generation with reinforced unlearning – start-page: 3520 volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst. year: 2017 ident: ref14 article-title: Certified defenses for data poisoning attacks – start-page: 13263 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2022 ident: ref37 article-title: The privacy onion effect: Memorization is relative – ident: ref98 doi: 10.1109/SP46214.2022.9833596 – ident: ref96 doi: 10.1016/j.clsr.2017.08.007 – ident: ref18 doi: 10.24963/ijcai.2022/556 – start-page: 689 volume-title: Proc. 28th Int. Conf. Mach. Learn. year: 2011 ident: ref105 article-title: Multimodal deep learning – ident: ref113 doi: 10.1109/EuroSP53844.2022.00027 – start-page: 4548 volume-title: Proc. Int. Conf. Mach. Learn. year: 2018 ident: ref33 article-title: Overcoming catastrophic forgetting with hard attention to the task – ident: ref78 doi: 10.1007/BF01582063 – year: 2023 ident: ref10 article-title: California consumer privacy act (CCPA) – ident: ref45 doi: 10.1109/5.726791 – start-page: 1 volume-title: Proc. 11th Int. Conf. Learn. Representations year: 2022 ident: ref83 article-title: Efficient model updates for approximate unlearning of graph-structured data – ident: ref35 doi: 10.1109/CVPR52729.2023.01929 – start-page: 1 volume-title: Proc. 5th Int. Conf. Learn. Representations year: 2017 ident: ref50 article-title: Pointer sentinel mixture models – ident: ref73 doi: 10.1109/CVPR46437.2021.00085 – ident: ref81 doi: 10.1145/3543507.3583521 – ident: ref48 doi: 10.1109/CVPR.2009.5206848 – ident: ref34 doi: 10.1145/3448016.3457239 – ident: ref97 doi: 10.1109/SP40001.2021.00106 – ident: ref110 doi: 10.14778/2824032.2824067 – ident: ref102 doi: 10.1109/TIFS.2024.3358993 – ident: ref36 doi: 10.1109/SP40001.2021.00019 – ident: ref74 doi: 10.24963/ijcai.2021/137 – ident: ref16 doi: 10.1109/SP.2015.35 – ident: ref41 doi: 10.1109/CVPR42600.2020.00932 – ident: ref56 doi: 10.1109/mc.2023.3333319 – ident: ref86 doi: 10.1145/3543507.3583305 – start-page: 3832 volume-title: Proc. Int. Conf. Mach. Learn. year: 2020 ident: ref43 article-title: Certified data removal from machine learning models – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref39 article-title: A zest of LIME: Towards architecture-independent model distances – ident: ref12 doi: 10.1109/EuroSP51992.2021.00028 – start-page: 18892 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2022 ident: ref65 article-title: Algorithms that approximate data removal: New results and limitations – start-page: 4007 volume-title: Proc. 31st USENIX Secur. Symp. year: 2022 ident: ref17 article-title: On the necessity of auditable algorithmic definitions for machine unlearning – ident: ref38 doi: 10.1007/978-3-031-20083-0_6 – year: 2022 ident: ref55 article-title: A survey of machine unlearning – ident: ref27 doi: 10.1007/978-3-030-45724-2_13 – volume: 12 start-page: 1069 issue: 3 year: 2011 ident: ref69 article-title: Differentially private empirical risk minimization publication-title: J. Mach. Learn. Res. – ident: ref20 doi: 10.1016/j.inffus.2019.12.012 – ident: ref2 doi: 10.1126/science.aaa8685 – start-page: 1885 volume-title: Proc. Int. Conf. Mach. Learn. year: 2017 ident: ref21 article-title: Understanding black-box predictions via influence functions – start-page: 13132 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. year: 2022 ident: ref68 article-title: Repairing neural networks by leaving the right past behind – ident: ref87 doi: 10.4324/9781003106715-8 – ident: ref53 doi: 10.1145/276675.276685 – ident: ref89 doi: 10.1145/3485447.3512222 – ident: ref29 doi: 10.1109/TIFS.2023.3265506 – ident: ref4 doi: 10.1126/science.aaa8415 – ident: ref28 doi: 10.1145/3319535.3354208 – ident: ref30 doi: 10.1145/3196494.3196517 – volume-title: Interpretable Machine Learning year: 2020 ident: ref115 |
| SSID | ssj0002951354 |
| Score | 2.549826 |
| Snippet | Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2150 |
| SubjectTerms | Adaptation models Computational modeling Data models Data points Machine learning machine learning security Machine unlearning Performance degradation Predictive models Random forests Taxonomy the right to be forgotten Training data |
| Title | Machine Unlearning: Solutions and Challenges |
| URI | https://ieeexplore.ieee.org/document/10488864 https://www.proquest.com/docview/3059523172 |
| Volume | 8 |
| WOSCitedRecordID | wos001201941100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2471-285X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002951354 issn: 2471-285X databaseCode: RIE dateStart: 20170101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEB1s8eDFD6xYrbIHb7p1u8luEm9SLHqweGiht7BNJiLIKv3w9zvJ7hZFFLztIQnhZZLMy87MA7jI5okspGGxdS6NuSWCQl64i5VCMiFfgh95EJsQ47GczdRTnawecmEQMQSfYd9_hn_59s2s_VMZ7XAyN5nzFrSEyKtkrc2DSkq-Ast4kxiTqOvJ3WT4QBQw5X3GBBGN5NvlE9RUfhzB4V4Z7f1zRvuwWzuQ0W214gewheUhXD2GmEiMpmUtA_F8E21evKKitNGwUU1ZdmA6ojnfx7UOQmwYT1YxdzJDOXd2gE4VqRDC-sKKzpmB5cwKJ1PGjeJYIPGdOePcOsxcJgX5AoQ-O4J2-VbiMUSFYo7n0mU5Wq5kXlgnQqSTNYqpRHVh0ACkTV0k3GtVvOpAFhKlA6jag6prULtwuenzXpXI-LN1x8P4pWWFYBd6zULoehstNR1GipgyOVknv3Q7hR0_ehW81YP2arHGM9g2H6uX5eI8WMgnxQC4Uw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA1aBb34gRWrVffgTbduN7ObxJuIpcW2eGiht7BNJiLIVvrh7zfJ7hZFFLztISHhZZLMy87MI-QqmUY844qG2pg4BG0JivXCTSgEWhNyJfgRvNgEGw75ZCKey2R1nwuDiD74DFvu0__L1zO1ck9ldodbc-MpbJKtBCCOinSt9ZNKbL0FmkCVGhOJ29Hj6KFnSWAMLUqZpRrRt-vH66n8OIT9zdLZ_-ecDshe6UIG98WaH5INzI_IzcBHRWIwzkshiJe7YP3mFWS5Dh4q3ZRFnYw7ds7dsFRCCBWFaBmC4QnyqdFtNCKLGWPalVY0RrU1UM0MjykoAZihZTxTCqANJibhzHoDFn96TGr5LMcTEmSCGki5SVLUIHiaacN8rJNWgopINEi7Akiqsky4U6t4k54uREJ6UKUDVZagNsj1us97USTjz9Z1B-OXlgWCDdKsFkKWG2kh7XEkLFe2btbpL90uyU53NOjLfm_4dEZ23UhFKFeT1JbzFZ6TbfWxfF3ML7y1fAKKBrua |
| 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=Machine+Unlearning%3A+Solutions+and+Challenges&rft.jtitle=IEEE+transactions+on+emerging+topics+in+computational+intelligence&rft.au=Xu%2C+Jie&rft.au=Wu%2C+Zihan&rft.au=Wang%2C+Cong&rft.au=Jia%2C+Xiaohua&rft.date=2024-06-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2471-285X&rft.volume=8&rft.issue=3&rft.spage=2150&rft_id=info:doi/10.1109%2FTETCI.2024.3379240&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2471-285X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2471-285X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2471-285X&client=summon |