skip to main content
10.1145/3604915.3608862acmconferencesArticle/Chapter ViewAbstractPublication PagesrecsysConference Proceedingsconference-collections
extended-abstract

Exploring Unlearning Methods to Ensure the Privacy, Security, and Usability of Recommender Systems

Published: 14 September 2023 Publication History

Abstract

Machine learning algorithms have proven highly effective in analyzing large amounts of data and identifying complex patterns and relationships. One application of machine learning that has received significant attention in recent years is recommender systems, which are algorithms that analyze user behavior and other data to suggest items or content that a user may be interested in. However useful, these systems may unintentionally retain sensitive, outdated, or faulty information. Posing a risk to user privacy, system security, and limiting a system’s usability. In this research proposal, we aim to address these challenges by investigating methods for machine “unlearning”, which would allow information to be efficiently “forgotten” or “unlearned” from machine learning models. The main objective of this proposal is to develop the foundation for future machine unlearning methods. We first evaluate current unlearning methods and explore novel adversarial attacks on these methods’ verifiability, efficiency, and accuracy to gain new insights and further develop the theory of machine unlearning. Using our gathered insights, we seek to create novel unlearning methods that are verifiable, efficient, and limit unnecessary accuracy degradation. Through this research, we seek to make significant contributions to the theoretical foundations of machine unlearning while also developing unlearning methods that can be applied to real-world problems.

References

[1]
Samyadeep Basu, Phillip Pope, and Soheil Feizi. 2021. Influence Functions in Deep Learning Are Fragile. In International Conference on Learning Representations 2021. Virtual Event. https://openreview.net/forum?id=xHKVVHGDOEk
[2]
Yinzhi Cao and Junfeng Yang. 2015. Towards Making Systems Forget with Machine Unlearning. In 2015 IEEE Symposium on Security and Privacy. IEEE, San Jose, CA, 463–480. https://doi.org/10.1109/SP.2015.35
[3]
Chong Chen, Fei Sun, Min Zhang, and Bolin Ding. 2022. Recommendation Unlearning. In Proceedings of the ACM Web Conference 2022. ACM, Virtual Event, Lyon France, 2768–2777. https://doi.org/10.1145/3485447.3511997
[4]
Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, and Yang Zhang. 2021. When Machine Unlearning Jeopardizes Privacy. In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. ACM, Virtual Event Republic of Korea, 896–911. https://doi.org/10.1145/3460120.3484756
[5]
James Davidson, Benjamin Liebald, Junning Liu, Palash Nandy, Taylor Van Vleet, Ullas Gargi, Sujoy Gupta, Yu He, Mike Lambert, Blake Livingston, and Dasarathi Sampath. 2010. The YouTube video recommendation system. In Proceedings of the fourth ACM conference on Recommender systems. ACM, Barcelona Spain, 293–296. https://doi.org/10.1145/1864708.1864770
[6]
Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, and Stefano Soatto. 2021. Mixed-Privacy Forgetting in Deep Networks. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Nashville, TN, USA, 792–801. https://doi.org/10.1109/CVPR46437.2021.00085
[7]
Carlos A. Gomez-Uribe and Neil Hunt. 2016. The Netflix Recommender System: Algorithms, Business Value, and Innovation. ACM Transactions on Management Information Systems 6, 4 (Jan. 2016), 1–19. https://doi.org/10.1145/2843948
[8]
Laura Graves, Vineel Nagisetty, and Vijay Ganesh. 2021. Amnesiac Machine Learning. Proceedings of the AAAI Conference on Artificial Intelligence 35, 13 (May 2021), 11516–11524. https://doi.org/10.1609/aaai.v35i13.17371
[9]
Hai Huang, Jiaming Mu, Neil Zhenqiang Gong, Qi Li, Bin Liu, and Mingwei Xu. 2021. Data Poisoning Attacks to Deep Learning Based Recommender Systems. In Proceedings 2021 Network and Distributed System Security Symposium. https://doi.org/10.14722/ndss.2021.24525 arXiv:2101.02644 [cs].
[10]
Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, and Chiyuan Zhang. 2023. Measuring Forgetting of Memorized Training Examples. In International Conference on Learning Representations 2023. Kigali, Rwanda. https://openreview.net/pdf?id=7bJizxLKrR arXiv:2207.00099 [cs].
[11]
Yuyuan Li, Xiaolin Zheng, Chaochao Chen, and Junlin Liu. 2022. Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation. http://arxiv.org/abs/2203.11491 arXiv:2203.11491 [cs].
[12]
Bo Liu, Ming Ding, Sina Shaham, Wenny Rahayu, Farhad Farokhi, and Zihuai Lin. 2022. When Machine Learning Meets Privacy: A Survey and Outlook. Comput. Surveys 54, 2 (March 2022), 1–36. https://doi.org/10.1145/3436755
[13]
Wenyan Liu, Juncheng Wan, Xiaoling Wang, Weinan Zhang, Dell Zhang, and Hang Li. 2022. Forgetting Fast in Recommender Systems. http://arxiv.org/abs/2208.06875 arXiv:2208.06875 [cs].
[14]
Jie Lu, Dianshuang Wu, Mingsong Mao, Wei Wang, and Guangquan Zhang. 2015. Recommender system application developments: A survey. Decision Support Systems 74 (June 2015), 12–32. https://doi.org/10.1016/j.dss.2015.03.008
[15]
Ananth Mahadevan and Michael Mathioudakis. 2021. Certifiable Machine Unlearning for Linear Models. http://arxiv.org/abs/2106.15093 arXiv:2106.15093 [cs].
[16]
Alessandro Mantelero. 2013. The EU Proposal for a General Data Protection Regulation and the roots of the ‘right to be forgotten’. Computer Law & Security Review 29, 3 (June 2013), 229–235. https://doi.org/10.1016/j.clsr.2013.03.010
[17]
Neil G. Marchant, Benjamin I. P. Rubinstein, and Scott Alfeld. 2022. Hard to Forget: Poisoning Attacks on Certified Machine Unlearning. Proceedings of the AAAI Conference on Artificial Intelligence 36, 7 (June 2022), 7691–7700. https://doi.org/10.1609/aaai.v36i7.20736
[18]
Pawel Matuszyk, João Vinagre, Myra Spiliopoulou, Alípio Mário Jorge, and João Gama. 2015. Forgetting methods for incremental matrix factorization in recommender systems. In Proceedings of the 30th Annual ACM Symposium on Applied Computing. ACM, Salamanca Spain, 947–953. https://doi.org/10.1145/2695664.2695820
[19]
Salvatore Mercuri, Raad Khraishi, Ramin Okhrati, Devesh Batra, Conor Hamill, Taha Ghasempour, and Andrew Nowlan. 2022. An Introduction to Machine Unlearning. http://arxiv.org/abs/2209.00939 arXiv:2209.00939 [cs].
[20]
Thanh Tam Nguyen, Thanh Trung Huynh, Phi Le Nguyen, Alan Wee-Chung Liew, Hongzhi Yin, and Quoc Viet Hung Nguyen. 2022. A Survey of Machine Unlearning. http://arxiv.org/abs/2209.02299 arXiv:2209.02299 [cs].
[21]
Sebastian Schelter. 2019. “Amnesia” – Towards Machine Learning Models That Can Forget User Data Very Fast. In 1st International Workshop on Applied AI for Database Systems and Applications. Los Angeles CA USA, 4. https://ssc.io/pdf/amnesia.pdf
[22]
Anvith Thudi, Hengrui Jia, Ilia Shumailov, and Nicolas Papernot. 2022. On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning. In 31st USENIX Security Symposium (USENIX Security 22). USENIX Association, Boston, MA, 4007–4022. https://www.usenix.org/system/files/sec22fall_thudi.pdf
[23]
Thi Ngoc Trang Tran, Alexander Felfernig, Christoph Trattner, and Andreas Holzinger. 2021. Recommender systems in the healthcare domain: state-of-the-art and research issues. Journal of Intelligent Information Systems 57, 1 (Aug. 2021), 171–201. https://doi.org/10.1007/s10844-020-00633-6
[24]
Benjamin Longxiang Wang and Sebastian Schelter. 2022. Efficiently Maintaining Next Basket Recommendations under Additions and Deletions of Baskets and Items. http://arxiv.org/abs/2201.13313 arXiv:2201.13313 [cs].
[25]
Wei Yuan, Hongzhi Yin, Fangzhao Wu, Shijie Zhang, Tieke He, and Hao Wang. 2022. Federated Unlearning for On-Device Recommendation. http://arxiv.org/abs/2210.10958 arXiv:2210.10958 [cs].

Cited By

View all
  • (2024)Efficient and Adaptive Recommendation Unlearning: A Guided Filtering Framework to Erase Outdated PreferencesACM Transactions on Information Systems10.1145/370663343:2(1-25)Online publication date: 5-Dec-2024
  • (2024)Machine Unlearning for Recommendation Systems: An InsightInnovative Computing and Communications10.1007/978-981-97-3817-5_30(415-430)Online publication date: 1-Aug-2024

Index Terms

  1. Exploring Unlearning Methods to Ensure the Privacy, Security, and Usability of Recommender Systems

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    RecSys '23: Proceedings of the 17th ACM Conference on Recommender Systems
    September 2023
    1406 pages
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 14 September 2023

    Check for updates

    Author Tags

    1. Machine Unlearning
    2. Recommender Systems
    3. Research Proposal

    Qualifiers

    • Extended-abstract
    • Research
    • Refereed limited

    Conference

    RecSys '23: Seventeenth ACM Conference on Recommender Systems
    September 18 - 22, 2023
    Singapore, Singapore

    Acceptance Rates

    Overall Acceptance Rate 254 of 1,295 submissions, 20%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)148
    • Downloads (Last 6 weeks)12
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Efficient and Adaptive Recommendation Unlearning: A Guided Filtering Framework to Erase Outdated PreferencesACM Transactions on Information Systems10.1145/370663343:2(1-25)Online publication date: 5-Dec-2024
    • (2024)Machine Unlearning for Recommendation Systems: An InsightInnovative Computing and Communications10.1007/978-981-97-3817-5_30(415-430)Online publication date: 1-Aug-2024

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media