Learn to Unlearn: Insights Into Machine Unlearning
Abstract
This article presents a comprehensive review of recent machine unlearning techniques, verification mechanisms, and potential attacks. We highlight emerging challenges and prospective research directions, aiming to provide valuable resources for integrating privacy, equity, and resilience into machine learning systems and help them “learn to unlearn.”
References
[1]
E. Chien, C. Pan, and O. Milenkovic, “Efficient model updates for approximate unlearning of graph-structured data,” in Proc. Int. Conf. Learn. Representations, 2023.
[2]
Y. Wu, E. Dobriban, and S. Davidson, “Deltagrad: Rapid retraining of machine learning models,” in Proc. Int. Conf. Mach. Learn., PMLR, 2020, pp. 10 355–10 366.
[3]
P. Voigt and A. Von dem Bussche, The EU General Data Protection Regulation (GDPR): A Practical Guide, 1st ed. Cham, Switzerland: Springer International Publishing, 2017.
[4]
Y. Cao and J. Yang, “Towards making systems forget with machine unlearning,” in Proc. IEEE Symp. Secur. Privacy, 2015, pp. 463–480.
[5]
C. Guo, T. Goldstein, A. Hannun, and L. Van Der Maaten, “Certified data removal from machine learning models,” in Proc. 37th Int. Conf. Mach. Learn., 2020, pp. 3832–3842.
[6]
Q. P. Nguyen, B. K. H. Low, and P. Jaillet, “Variational Bayesian unlearning,” in Proc. Adv. Neural Inf. Process. Syst., 2020, vol. 33, pp. 16,025–16,036.
[7]
L. Bourtoule et al., “Machine unlearning,” in Proc. IEEE Symp. Security Privacy (SP), 2021, pp. 141–159.
[8]
J. Brophy and D. Lowd, “Machine unlearning for random forests,” in Proc. Int. Conf. Mach. Learn., PMLR, 2021, pp. 1092–1104.
[9]
A. Golatkar, A. Achille, and S. Soatto, “Eternal sunshine of the spotless net: Selective forgetting in deep networks,” in Proc. IEEE/CVF Conf. Comput. Vision Pattern Recognit., 2020, pp. 9301–9309.
[10]
A. Sekhari, J. Acharya, G. Kamath, and A. T. Suresh, “Remember what you want to forget: Algorithms for machine unlearning,” in Proc. Adv. Neural Inf. Process. Syst., 2021, vol. 34, pp. 18,075–18,086.
[11]
A. Ginart, M. Guan, G. Valiant, and J. Y. Zou, “Making AI forget you: Data deletion in machine learning,” in Proc. Adv. Neural Inf. Process. Syst., 2019, vol. 32, pp. 3518–3531.
[12]
D. M. Sommer, L. Song, S. Wagh, and P. Mittal, “Athena: Probabilistic verification of machine unlearning,” Proc. Privacy Enhancing Technol., vol. 3, pp. 268–290, Jul. 2022.
[13]
M. Chen, Z. Zhang, T. Wang, M. Backes, M. Humbert, and Y. Zhang, “When machine unlearning jeopardizes privacy,” in Proc. ACM SIGSAC Conf. Comput. Commun. Security, 2021, pp. 896–911.
[14]
N. G. Marchant, B. I. Rubinstein, and S. Alfeld, “Hard to forget: Poisoning attacks on certified machine unlearning,” in Proc. AAAI Conf. Artif. Intell., 2022, vol. 36, no. 7, pp. 7691–7700.
[15]
R. Shokri, M. Stronati, C. Song, and V. Shmatikov, “Membership inference attacks against machine learning models,” in Proc. IEEE Symp. Security Privacy (SP), 2017, pp. 3–18.
Index Terms
- Learn to Unlearn: Insights Into Machine Unlearning
Index terms have been assigned to the content through auto-classification.
Recommendations
Machine Unlearning in Learned Databases: An Experimental Analysis
SIGMODMachine learning models based on neural networks (NNs) are enjoying ever-increasing attention in the Database (DB) community, both in research and practice. However, an important issue has been largely overlooked, namely the challenge of dealing with the ...
Comments
Information & Contributors
Information
Published In
0018-9162 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Computer Society Press
Washington, DC, United States
Publication History
Published: 06 March 2024
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 16 Oct 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in