Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects (2403.08254v1)

Published 13 Mar 2024 in cs.LG, cs.CR, and cs.CY

Abstract: Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. Data users have been endowed with the right to be forgotten of their data. In the course of ML, the forgotten right requires a model provider to delete user data and its subsequent impact on ML models upon user requests. Machine unlearning emerges to address this, which has garnered ever-increasing attention from both industry and academia. While the area has developed rapidly, there is a lack of comprehensive surveys to capture the latest advancements. Recognizing this shortage, we conduct an extensive exploration to map the landscape of machine unlearning including the (fine-grained) taxonomy of unlearning algorithms under centralized and distributed settings, debate on approximate unlearning, verification and evaluation metrics, challenges and solutions for unlearning under different applications, as well as attacks targeting machine unlearning. The survey concludes by outlining potential directions for future research, hoping to serve as a guide for interested scholars.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (141)
  1. 2018. California consumer privacy act (CCPA). https://oag.ca.gov/privacy/ccpa.
  2. 2018. General data protection regulation GDPR. https://gdpr-info.eu/.
  3. Aditya Golatkar and Alessandro Achille and Stefano Soatto. 2020. Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIX (Lecture Notes in Computer Science, Vol. 12374). 383–398.
  4. A Closer Look at Memorization in Deep Networks. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017 (Proceedings of Machine Learning Research, Vol. 70). 233–242.
  5. Unsupervised Unlearning of Concept Drift with Autoencoders. In IEEE Symposium Series on Computational Intelligence, SSCI 2023, Mexico City, Mexico, December 5-8, 2023. IEEE, 703–710.
  6. Ayush Kumar Tarun and Vikram Singh Chundawat and Murari Mandal and Mohan S. Kankanhalli. 2023. Deep Regression Unlearning. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202). 33921–33939.
  7. Peter J. Bevan and Amir Atapour-Abarghouei. 2022. Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 1874–1892.
  8. Machine Unlearning. In 42nd IEEE Symposium on Security and Privacy, SP 2021, San Francisco, CA, USA, 24-27 May 2021. 141–159.
  9. Jonathan Brophy and Daniel Lowd. 2021. Machine Unlearning for Random Forests. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139). 1092–1104.
  10. IPGuard: Protecting intellectual property of deep neural networks via fingerprinting the classification boundary. In Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security. 14–25.
  11. Yinzhi Cao and Junfeng Yang. 2015. Towards Making Systems Forget with Machine Unlearning. In 2015 IEEE Symposium on Security and Privacy, SP 2015, San Jose, CA, USA, May 17-21, 2015. 463–480.
  12. Efficient Repair of Polluted Machine Learning Systems via Causal Unlearning. In Proceedings of the 2018 on Asia Conference on Computer and Communications Security, AsiaCCS 2018, Incheon, Republic of Korea, June 04-08, 2018. 735–747.
  13. The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks. In 28th USENIX Security Symposium, USENIX Security 2019, Santa Clara, CA, USA, August 14-16, 2019. 267–284.
  14. Gert Cauwenberghs and Tomaso A. Poggio. 2000. Incremental and Decremental Support Vector Machine Learning. In Advances in Neural Information Processing Systems 13, Papers from Neural Information Processing Systems (NIPS) 2000, Denver, CO, USA. MIT Press, 409–415.
  15. Fast Federated Machine Unlearning with Nonlinear Functional Theory. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202). 4241–4268.
  16. Recommendation Unlearning. In WWW ’22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25 - 29, 2022. ACM, 2768–2777.
  17. Jiaao Chen and Diyi Yang. 2023. Unlearn what you want to forget: Efficient unlearning for llms. arXiv preprint arXiv:2310.20150 (2023).
  18. Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. 7766–7775.
  19. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021).
  20. When Machine Unlearning Jeopardizes Privacy. In CCS ’21: 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, Republic of Korea, November 15 - 19, 2021. ACM, 896–911.
  21. A novel online incremental and decremental learning algorithm based on variable support vector machine. Clust. Comput. 22, Supplement (2019), 7435–7445.
  22. Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science 381, 6664 (2023), eadg7492.
  23. Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks Using an Incompetent Teacher. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023. 7210–7217.
  24. Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks. CoRR abs/2212.10717 (2022). https://doi.org/10.48550/ARXIV.2212.10717 arXiv:2212.10717
  25. Lifelong Anomaly Detection Through Unlearning. In Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, CCS 2019, London, UK, November 11-15, 2019. ACM, 1283–1297.
  26. Decremental learning algorithms for nonlinear langrangian and least squares support vector machines. In Proceedings of the First International Symposium on Optimization and Systems Biology (OSB’07). 358–366.
  27. Verifiable and Provably Secure Machine Unlearning. (Oct 2022).
  28. Ronen Eldan and Mark Russinovich. 2023. Who’s Harry Potter? Approximate Unlearning in LLMs. (Oct 2023).
  29. Holly Else. 2023. Abstracts written by ChatGPT fool scientists. Nature (Jan 2023), 423–423.
  30. Fast Model Update for IoT Traffic Anomaly Detection With Machine Unlearning. IEEE Internet Things J. 10, 10 (2023), 8590–8602.
  31. Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale. In Proceedings of the 10th International Conference on Operations Research and Enterprise Systems.
  32. Model inversion attacks that exploit confidence information and basic countermeasures. In Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 1322–1333.
  33. VFL: A Verifiable Federated Learning With Privacy-Preserving for Big Data in Industrial IoT. IEEE Trans. Ind. Informatics 18, 5 (2022), 3316–3326. https://doi.org/10.1109/TII.2020.3036166
  34. Unlearning Protected User Attributes in Recommendations with Adversarial Training. In SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022. 2142–2147.
  35. Property Inference Attacks on Fully Connected Neural Networks using Permutation Invariant Representations. In Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, CCS 2018, Toronto, ON, Canada, October 15-19, 2018. 619–633.
  36. Verifi: Towards verifiable federated unlearning. arXiv preprint arXiv:2205.12709 (2022).
  37. Backdoor attacks and countermeasures on deep learning: A comprehensive review. arXiv preprint arXiv:2007.10760 (2020).
  38. A Swiss Army Infinitesimal Jackknife. In The 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019, 16-18 April 2019, Naha, Okinawa, Japan (Proceedings of Machine Learning Research, Vol. 89). 1139–1147.
  39. Evaluating Inexact Unlearning Requires Revisiting Forgetting. CoRR abs/2201.06640 (2022). arXiv:2201.06640
  40. Mixed-Privacy Forgetting in Deep Networks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021. 792–801.
  41. Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. 9301–9309.
  42. Amnesiac Machine Learning. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. 11516–11524.
  43. Certified Data Removal from Machine Learning Models. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). 3832–3842.
  44. Verifying in the Dark: Verifiable Machine Unlearning by Using Invisible Backdoor Triggers. IEEE Trans. Inf. Forensics Secur. 19 (2024), 708–721.
  45. Adaptive Machine Unlearning. Neural Information Processing Systems,Neural Information Processing Systems (Dec 2021).
  46. DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks. CoRR abs/2105.06209 (2021). arXiv:2105.06209
  47. DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks. arXiv: Learning,arXiv: Learning (May 2021).
  48. A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services. CoRR abs/2309.08230 (2023). https://doi.org/10.48550/ARXIV.2309.08230 arXiv:2309.08230
  49. Approximate Data Deletion from Machine Learning Models. In The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, April 13-15, 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 130). 2008–2016.
  50. Sharu Theresa Jose and Osvaldo Simeone. 2021. A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization. In 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), Gold Coast, Australia, October 25-28, 2021. 1–6.
  51. Highly accurate protein structure prediction with AlphaFold. Nature 596, 7873 (2021), 583–589.
  52. Masayuki Karasuyama and Ichiro Takeuchi. 2010. Multiple incremental decremental learning of support vector machines. IEEE Trans. Neural Networks 21, 7 (2010), 1048–1059.
  53. Rasha Kashef. 2021. A boosted SVM classifier trained by incremental learning and decremental unlearning approach. Expert Syst. Appl. 167 (2021), 114154.
  54. Junyaup Kim and Simon S. Woo. 2022. Efficient Two-stage Model Retraining for Machine Unlearning. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2022, New Orleans, LA, USA, June 19-20, 2022. 4360–4368.
  55. Pang Wei Koh and Percy Liang. 2017. Understanding Black-box Predictions via Influence Functions. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017 (Proceedings of Machine Learning Research, Vol. 70). PMLR, 1885–1894.
  56. Towards Unbounded Machine Unlearning. CoRR abs/2302.09880 (2023). https://doi.org/10.48550/ARXIV.2302.09880 arXiv:2302.09880
  57. Jens Leysen. 2023. Exploring Unlearning Methods to Ensure the Privacy, Security, and Usability of Recommender Systems. In Proceedings of the 17th ACM Conference on Recommender Systems, RecSys 2023, Singapore, Singapore, September 18-22, 2023. 1300–1304.
  58. Selective and collaborative influence function for efficient recommendation unlearning. Expert Syst. Appl. 234 (2023), 121025.
  59. Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation. CoRR abs/2203.11491 (2022). https://doi.org/10.48550/ARXIV.2203.11491 arXiv:2203.11491
  60. ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. 20147–20155.
  61. Continual learning and private unlearning. In Conference on Lifelong Learning Agents. PMLR, 243–254.
  62. Continual Learning and Private Unlearning. In Conference on Lifelong Learning Agents, CoLLAs 2022, 22-24 August 2022, McGill University, Montréal, Québec, Canada (Proceedings of Machine Learning Research, Vol. 199). PMLR, 243–254.
  63. FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models. In 29th IEEE/ACM International Symposium on Quality of Service, IWQOS 2021, Tokyo, Japan, June 25-28, 2021. 1–10.
  64. Recommendation Unlearning via Matrix Correction. CoRR abs/2307.15960 (2023). https://doi.org/10.48550/ARXIV.2307.15960 arXiv:2307.15960
  65. Backdoor Defense with Machine Unlearning. In IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, London, United Kingdom, May 2-5, 2022. 280–289.
  66. The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining. In IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, London, United Kingdom, May 2-5, 2022. 1749–1758.
  67. A survey on federated unlearning: Challenges, methods, and future directions. arXiv preprint arXiv:2310.20448 (2023).
  68. Effective Machine Learning-based Access Control Administration through Unlearning. In IEEE European Symposium on Security and Privacy, EuroS&P 2023 - Workshops, Delft, Netherlands, July 3-7, 2023. IEEE, 50–57.
  69. FP22{}^{\mbox{2}}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPT-MIA: A Membership Inference Attack Free of Posterior Probability in Machine Unlearning. In Provable and Practical Security - 16th International Conference, ProvSec 2022, Nanjing, China, November 11-12, 2022, Proceedings (Lecture Notes in Computer Science, Vol. 13600). 167–175.
  70. Learn to Forget: Machine Unlearning via Neuron Masking. IEEE Trans. Dependable Secur. Comput. 20, 4 (2023), 3194–3207.
  71. TOFU: A Task of Fictitious Unlearning for LLMs. (Jan 2024).
  72. Hard to Forget: Poisoning Attacks on Certified Machine Unlearning. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022. 7691–7700.
  73. James Martens. 2020. New insights and perspectives on the natural gradient method. The Journal of Machine Learning Research 21, 1 (2020), 5776–5851.
  74. Deep Unlearning via Randomized Conditionally Independent Hessians. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. 10412–10421.
  75. An introduction to machine unlearning. arXiv preprint arXiv:2209.00939 (2022).
  76. Min Chen and Zhikun Zhang and Tianhao Wang and Michael Backes and Mathias Humbert and Yang Zhang. 2022. Graph Unlearning. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, CCS 2022, Los Angeles, CA, USA, November 7-11, 2022. 499–513.
  77. Deep Learning Based Caching for Self-Driving Cars in Multi-Access Edge Computing. IEEE Transactions on Intelligent Transportation Systems (May 2021), 2862–2877.
  78. Descent-to-Delete: Gradient-Based Methods for Machine Unlearning. In Algorithmic Learning Theory, 16-19 March 2021, Virtual Conference, Worldwide (Proceedings of Machine Learning Research, Vol. 132). 931–962.
  79. A survey of machine unlearning. arXiv preprint arXiv:2209.02299 (2022).
  80. Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual.
  81. Jiaul H. Paik. 2013. A novel TF-IDF weighting scheme for effective ranking. In The 36th International ACM SIGIR conference on research and development in Information Retrieval, SIGIR ’13, Dublin, Ireland - July 28 - August 01, 2013. ACM, 343–352.
  82. On Model Outsourcing Adaptive Attacks to Deep Learning Backdoor Defenses. IEEE Transactions on Information Forensics and Security (2024).
  83. Learn to Unlearn: Insights into Machine Unlearning. (2023).
  84. Vikas Ramachandra and Mohit Sethi. 2023. Machine Unlearning for Causal Inference. arXiv preprint arXiv:2308.13559 (2023).
  85. Incremental and Decremental Learning for Linear Support Vector Machines. In Artificial Neural Networks - ICANN 2007, 17th International Conference, Porto, Portugal, September 9-13, 2007, Proceedings, Part I (Lecture Notes in Computer Science, Vol. 4668). 209–218.
  86. Graph Unlearning: A Review. (Aug 2023).
  87. Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning. Cornell University - arXiv,Cornell University - arXiv (Apr 2019).
  88. Sebastian Schelter. 2020. ”Amnesia” - Machine Learning Models That Can Forget User Data Very Fast. In 10th Conference on Innovative Data Systems Research, CIDR 2020, Amsterdam, The Netherlands, January 12-15, 2020, Online Proceedings.
  89. HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning. In SIGMOD ’21: International Conference on Management of Data, Virtual Event, China, June 20-25, 2021. 1545–1557.
  90. Sebastian Schelter. 2021. Towards Efficient Machine Unlearning via Incremental View Maintenance. In Workshop on Challenges in Deploying and Monitoring ML Systems at the International Conference on Machine Learning ICML, June, 2021.
  91. Remember What You Want to Forget: Algorithms for Machine Unlearning. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. 18075–18086.
  92. Exploring the landscape of machine unlearning: A comprehensive survey and taxonomy. arXiv preprint arXiv:2305.06360 (2023).
  93. Membership Inference Attacks Against Machine Learning Models. In 2017 IEEE Symposium on Security and Privacy, SP 2017, San Jose, CA, USA, May 22-26, 2017. 3–18.
  94. Knowledge unlearning for llms: Tasks, methods, and challenges. arXiv preprint arXiv:2311.15766 (2023).
  95. Towards Probabilistic Verification of Machine Unlearning. CoRR abs/2003.04247 (2020). arXiv:2003.04247
  96. Lessons Learned: Defending Against Property Inference Attacks. In Proceedings of the 20th International Conference on Security and Cryptography, SECRYPT 2023, Rome, Italy, July 10-12, 2023. SCITEPRESS, 312–323.
  97. Chris Stokel-Walker and Richard Van Noorden. 2023. What ChatGPT and generative AI mean for science. Nature (Feb 2023), 214–216.
  98. Machine unlearning: Its need and implementation strategies. In 2021 Thirteenth International Conference on Contemporary Computing (IC3-2021). 241–246.
  99. Fast Yet Effective Machine Unlearning. CoRR abs/2111.08947 (2021). arXiv:2111.08947
  100. Unrolling SGD: Understanding Factors Influencing Machine Unlearning. In 7th IEEE European Symposium on Security and Privacy, EuroS&P 2022, Genoa, Italy, June 6-10, 2022. 303–319.
  101. On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning. In 31st USENIX Security Symposium, USENIX Security 2022, Boston, MA, USA, August 10-12, 2022. 4007–4022.
  102. Adapt then Unlearn: Exploiting Parameter Space Semantics for Unlearning in Generative Adversarial Networks. arXiv preprint arXiv:2309.14054 (2023).
  103. Incremental and decremental training for linear classification. In The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’14, New York, NY, USA - August 24 - 27, 2014. 343–352.
  104. Incremental and Decremental Proximal Support Vector Classification using Decay Coefficients. In Data Warehousing and Knowledge Discovery, 5th International Conference, DaWaK 2003, Prague, Czech Republic, September 3-5,2003, Proceedings (Lecture Notes in Computer Science, Vol. 2737). 422–423.
  105. Machine Unlearning via Algorithmic Stability. In Conference on Learning Theory, COLT 2021, 15-19 August 2021, Boulder, Colorado, USA (Proceedings of Machine Learning Research, Vol. 134). 4126–4142.
  106. Vikram S. Chundawat and Ayush K. Tarun and Murari Mandal and Mohan S. Kankanhalli. 2023. Zero-Shot Machine Unlearning. IEEE Trans. Inf. Forensics Secur. 18 (2023), 2345–2354.
  107. Inductive Graph Unlearning. In 32nd USENIX Security Symposium, USENIX Security 2023, Anaheim, CA, USA, August 9-11, 2023. 3205–3222.
  108. Federated Unlearning via Class-Discriminative Pruning. In WWW ’22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25 - 29, 2022. 622–632.
  109. KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023. 13264–13276.
  110. BFU: Bayesian Federated Unlearning with Parameter Self-Sharing. In Proceedings of the 2023 ACM Asia Conference on Computer and Communications Security, ASIA CCS 2023, Melbourne, VIC, Australia, July 10-14, 2023. ACM, 567–578.
  111. Machine Unlearning of Features and Labels. In 30th Annual Network and Distributed System Security Symposium, NDSS 2023, San Diego, California, USA, February 27 - March 3, 2023.
  112. Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples. CoRR abs/2307.10562 (2023). https://doi.org/10.48550/ARXIV.2307.10562 arXiv:2307.10562
  113. Federated Unlearning with Knowledge Distillation. CoRR abs/2201.09441 (2022). arXiv:2201.09441
  114. GIF: A General Graph Unlearning Strategy via Influence Function. In Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023. ACM, 651–661.
  115. Certified Edge Unlearning for Graph Neural Networks. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023, Long Beach, CA, USA, August 6-10, 2023. 2606–2617.
  116. Federated Unlearning: Guarantee the Right of Clients to Forget. IEEE Netw. 36, 5 (2022), 129–135.
  117. DeltaGrad: Rapid retraining of machine learning models. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). 10355–10366.
  118. PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models. In Proceedings of the 2020 International Conference on Management of Data, SIGMOD Conference 2020, online conference [Portland, OR, USA], June 14-19, 2020. 447–462.
  119. Machine Unlearning: A Survey. ACM Comput. Surv. 56, 1 (2024), 9:1–9:36.
  120. Machine unlearning: Solutions and challenges. arXiv preprint arXiv:2308.07061 (2023).
  121. Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations. CoRR abs/2302.06676 (2023). https://doi.org/10.48550/ARXIV.2302.06676 arXiv:2302.06676
  122. ARCANE: An Efficient Architecture for Exact Machine Unlearning. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022. ijcai.org, 4006–4013.
  123. Jiaxi Yang and Yang Zhao. 2023. A Survey of Federated Unlearning: A Taxonomy, Challenges and Future Directions. arXiv preprint arXiv:2310.19218 (2023).
  124. Li Yang and Abdallah Shami. 2020. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing 415 (2020), 295–316.
  125. Diffusion Models: A Comprehensive Survey of Methods and Applications. (Sep 2022).
  126. Large language model unlearning. arXiv preprint arXiv:2310.10683 (2023).
  127. Model Inversion Attack against Transfer Learning: Inverting a Model without Accessing It. CoRR abs/2203.06570 (2022).
  128. Split Unlearning. CoRR abs/2308.10422 (2023). https://doi.org/10.48550/ARXIV.2308.10422 arXiv:2308.10422
  129. Federated Unlearning for On-Device Recommendation. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, WSDM 2023, Singapore, 27 February 2023 - 3 March 2023. 393–401.
  130. A Survey of Autonomous Driving: Common Practices and Emerging Technologies. IEEE Access (Jan 2020), 58443–58469.
  131. Adversarial Unlearning of Backdoors via Implicit Hypergradient. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022.
  132. Toward Highly-Efficient and Accurate Services QoS Prediction via Machine Unlearning. IEEE Access 11 (2023), 76242–76254.
  133. A review on machine unlearning. SN Computer Science 4, 4 (2023), 337.
  134. Poison Ink: Robust and Invisible Backdoor Attack. IEEE Trans. Image Process. 31 (2022), 5691–5705.
  135. FedRecovery: Differentially Private Machine Unlearning for Federated Learning Frameworks. IEEE Trans. Inf. Forensics Secur. 18 (2023), 4732–4746.
  136. Recommendation Unlearning via Influence Function. CoRR abs/2307.02147 (2023). https://doi.org/10.48550/ARXIV.2307.02147 arXiv:2307.02147
  137. Poison Neural Network-Based mmWave Beam Selection and Detoxification With Machine Unlearning. IEEE Trans. Commun. 71, 2 (2023), 877–892.
  138. Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization. In NeurIPS.
  139. Privacy-Preserving Federated Learning in Fog Computing. IEEE Internet Things J. 7, 11 (2020), 10782–10793. https://doi.org/10.1109/JIOT.2020.2987958
  140. PPA: Preference Profiling Attack Against Federated Learning. In 30th Annual Network and Distributed System Security Symposium, NDSS 2023, San Diego, California, USA, February 27 - March 3, 2023. The Internet Society.
  141. Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning. In Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023. 2444–2454.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Na Li (227 papers)
  2. Chunyi Zhou (14 papers)
  3. Yansong Gao (72 papers)
  4. Hui Chen (298 papers)
  5. Anmin Fu (24 papers)
  6. Zhi Zhang (113 papers)
  7. Yu Shui (1 paper)
Citations (1)
View on Semantic Scholar