{"type":"ScholarlyArticle","title":"Unlearning during Learning: An Efficient Federated Machine Unlearning Method","authors":[{"name":"Hanlin Gu","slug":"hanlin-gu","given":"Hanlin","family":"Gu","affiliation":"AI Lab , Webank ,"},{"name":"Gongxi Zhu","slug":"gongxi-zhu","given":"Gongxi","family":"Zhu","affiliation":"University of Electronic Science Technology of China ,; Shenzhen International Graduate School , Tsinghua University ,"},{"name":"Jie Zhang","slug":"jie-zhang","given":"Jie","family":"Zhang","affiliation":"Nanyang Technological University"},{"name":"Xinyuan Zhao","slug":"xinyuan-zhao","given":"Xinyuan","family":"Zhao","affiliation":"Shenzhen International Graduate School , Tsinghua University ,"},{"name":"Yuxing Han","slug":"yuxing-han","given":"Yuxing","family":"Han","affiliation":"Shenzhen International Graduate School , Tsinghua University ,"},{"name":"Lixin Fan","slug":"lixin-fan","given":"Lixin","family":"Fan","affiliation":"AI Lab , Webank ,"},{"name":"Qiang Yang","slug":"qiang-yang","given":"Qiang","family":"Yang","affiliation":"AI Lab , Webank ,"}],"abstract":"In recent years, Federated Learning (FL) has garnered significant attention as a distributed machine learning paradigm. To facilitate the implementation of the \"right to be forgotten,\" the concept of federated machine unlearning (FMU) has also emerged. However, current FMU approaches often involve additional time-consuming steps and may not offer comprehensive unlearning capabilities, which renders them less practical in real FL scenarios. In this paper, we introduce FedAU, an innovative and efficient FMU framework aimed at overcoming these limitations. Specifically, FedAU incorporates a lightweight auxiliary unlearning module into the learning process and employs a straightforward linear operation to facilitate unlearning. This approach eliminates the requirement for extra time-consuming steps, rendering it well-suited for FL.\r\nFurthermore, FedAU exhibits remarkable versatility. It not only enables multiple clients to carry out unlearning tasks concurrently but also supports unlearning at various levels of granularity, including individual data samples, specific classes, and even at the client level. We conducted extensive experiments on MNIST, CIFAR10, and CIFAR100 datasets to evaluate the performance of FedAU. The results demonstrate that FedAU effectively achieves the desired unlearning effect while maintaining model accuracy.","doi":"10.24963/ijcai.2024/446","url":"https://ijcai.org/proceedings/2024/446","pdf":"https://ijcai.org/proceedings/2024/0446.pdf","markdown":"https://ijcai.org/proceedings/2024/446.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/446","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":446,"pages":{"first":4035,"last":4043},"keywords":["Machine Learning: ML: Federated learning","Multidisciplinary Topics and Applications: MTA: Security and privacy"],"videos":[],"references":[{"position":1,"raw":"[Bourtoule et al., 2021] Lucas Bourtoule, Varun Chan- drasekaran, Christopher A Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. Machine unlearning. In 2021 IEEE Symposium on Security and Privacy (SP), pages 141-159. IEEE, 2021.","title":"Machine unlearning","authors":"Lucas Bourtoule, Varun Chandrasekaran, Christopher A Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot","year":"2021","venue":"IEEE Symposium on Security and Privacy (SP)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Che et al., 2023] Tianshi Che, Yang Zhou, Zijie Zhang, Lingjuan Lyu, Ji Liu, Da Yan, Dejing Dou, and Jun Huan. Fast federated machine unlearning with nonlinear func- tional theory. In International conference on machine learning, pages 4241-4268. PMLR, 2023.","title":"Fast federated machine unlearning with nonlinear functional theory","authors":"Tianshi Che, Yang Zhou, Zijie Zhang, Lingjuan Lyu, Ji Liu, Da Yan, Dejing Dou, Jun Huan","year":"2023","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2023] Min Chen, Weizhuo Gao, Gaoyang Liu, Kai Peng, and Chen Wang. Boundary unlearning: Rapid forgetting of deep networks via shifting the decision boundary. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7766- 7775, 2023.","title":"Boundary unlearning: Rapid forgetting of deep networks via shifting the decision boundary","authors":"Chen","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng et al., 2020] Yong Cheng, Yang Liu, Tianjian Chen, and Qiang Yang. Federated learning for privacy- preserving ai. Communications of the ACM, 63(12):33-36, 2020.","title":"Federated learning for privacypreserving ai","authors":"Yong Cheng, Yang Liu, Tianjian Chen, Qiang Yang","year":"2020","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Deng et al., 2020] Yuyang Deng, Mohammad Mahdi Ka- mani, and Mehrdad Mahdavi. Distributionally robust fed- erated averaging. Advances in neural information process- ing systems, 33:15111-15122, 2020.","title":"Distributionally robust federated averaging","authors":"Yuyang Deng, Mohammad Mahdi Kamani, Mehrdad Mahdavi","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dwork, 2006] Cynthia Dwork. Differential privacy. In In- ternational colloquium on automata, languages, and pro- gramming, pages 1-12. Springer, 2006.","title":"Differential privacy","authors":"Cynthia Dwork","year":"2006","venue":"International colloquium on automata, languages, and programming","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Eisenhofer et al., 2022] Thorsten Eisenhofer, Doreen Rie- pel, Varun Chandrasekaran, Esha Ghosh, O. Ohrimenko, and Nicolas Papernot. Verifiable and provably secure ma- chine unlearning. ArXiv, abs/2210.09126, 2022.","title":"Verifiable and provably secure machine unlearning","authors":"Thorsten Eisenhofer, Doreen Riepel, Varun Chandrasekaran, Esha Ghosh, O Ohrimenko, Nicolas Papernot","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gao et al., 2022] Xiangshan Gao, Xingjun Ma, Jingyi Wang, Youcheng Sun, Bo Li, Shouling Ji, Peng Cheng, and Jiming Chen. Verifi: Towards verifiable federated un- learning. arXiv preprint arXiv:2205.12709, 2022.","title":"Verifi: Towards verifiable federated unlearning","authors":"Gao","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Goldreich, 1998] Oded Goldreich. Secure multi-party com- putation. Manuscript. Preliminary version, 78(110):1- 108, 1998.","title":"Secure multi-party computation","authors":"Oded Goldreich","year":"1998","venue":"Manuscript. Preliminary version","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Graves et al., 2021] Laura Graves, Vineel Nagisetty, and Vijay Ganesh. Amnesiac machine learning. In Proceed- ings of the AAAI Conference on Artificial Intelligence, vol- ume 35, pages 11516-11524, 2021.","title":"Laura Graves, Vineel Nagisetty, and Vijay Ganesh. Amnesiac machine learning","authors":"Graves","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Halimi et al., 2022] Anisa Halimi, Swanand Ravindra Kadhe, Ambrish Rawat, and Nathalie Baracaldo Angel. Federated unlearning: How to efficiently erase a client in fl? In International Conference on Machine Learning, 2022.","title":"Federated unlearning: How to efficiently erase a client in fl?","authors":"Anisa Halimi, Swanand Ravindra Kadhe, Ambrish Rawat, Nathalie Baracaldo Angel","year":"2022","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Harding et al., 2019] Elizabeth Liz Harding, Jarno J Vanto, Reece Clark, L Hannah Ji, and Sara C Ainsworth. Under- standing the scope and impact of the california consumer privacy act of 2018. Journal of Data Protection & Privacy, 2(3):234-253, 2019.","title":"Understanding the scope and impact of the california consumer privacy act of 2018","authors":"Liz Elizabeth, Jarno J Harding, Reece Vanto, L Clark, Ji Hannah, Sara C Ainsworth","year":"2019","venue":"Journal of Data Protection & Privacy","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[He et al., 2019] Zecheng He, Tianwei Zhang, and Ruby B Lee. Model inversion attacks against collaborative infer- ence. In Proceedings of the 35th Annual Computer Secu- rity Applications Conference, pages 148-162, 2019.","title":"Model inversion attacks against collaborative inference","authors":"He","year":"2019","venue":"Proceedings of the 35th Annual Computer Security Applications Conference","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Jose and Simeone, 2021] Sharu Theresa Jose and O. Sime- one. A unified pac-bayesian framework for machine un- learning via information risk minimization. 2021 IEEE 31st International Workshop on Machine Learning for Sig- nal Processing (MLSP), pages 1-6, 2021.","title":"A unified pac-bayesian framework for machine unlearning via information risk minimization","authors":"Sharu Theresa, Jose, O Simeone","year":"2021","venue":"IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Konečnỳ et al., 2015] Jakub Konečnỳ, Brendan McMahan, and Daniel Ramage. Federated optimization: Distributed optimization beyond the datacenter. arXiv preprint arXiv:1511.03575, 2015.","title":"Federated optimization: Distributed optimization beyond the datacenter","authors":"Jakub Konečnỳ, Brendan Mcmahan, Daniel Ramage","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In F. Pereira, C.J. Burges, L. Bottou, and K.Q. Weinberger, editors, Advances in Neu- ral Information Processing Systems, volume 25.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"Curran Associates, Inc., 2012.","title":null,"authors":"Curran Associates, Inc","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Krizhevsky et al., 2014] Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton. The cifar-10 dataset. online: http://www. cs. toronto. edu/kriz/cifar. html, 55(5), 2014.","title":"The cifar-10 dataset","authors":"Alex Krizhevsky, Vinod Nair, Geoffrey Hinton","year":"2014","venue":null,"doi":null,"url":"http://www.cs.toronto.edu/kriz/cifar.html,55","internal_url":null},{"position":20,"raw":"[LeCun et al., 1998] Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning ap- plied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[LeCun et al., 2010] Yann LeCun, Corinna Cortes, and CJ Burges. Mnist handwritten digit database. ATT Labs [Online]. Available: http://yann.lecun.com/exdb/mnist, 2, 2010.","title":"Mnist handwritten digit database","authors":"Yann Lecun, Corinna Cortes, Burges","year":"2010","venue":null,"doi":null,"url":"http://yann.lecun.com/exdb/mnist,2","internal_url":null},{"position":22,"raw":"[Li et al., 2022] Qinbin Li, Yiqun Diao, Quan Chen, and Bingsheng He. Federated learning on non-iid data silos: An experimental study. In 2022 IEEE 38th International Conference on Data Engineering (ICDE), pages 965-978. IEEE, 2022.","title":"Federated learning on non-iid data silos: An experimental study","authors":"Li","year":"2022","venue":"IEEE 38th International Conference on Data Engineering (ICDE)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liu et al., 2021] Gaoyang Liu, Xiaoqiang Ma, Yang Yang, Chen Wang, and Jiangchuan Liu. Federaser: Enabling ef- ficient client-level data removal from federated learning models. In 2021 IEEE/ACM 29th International Sympo- sium on Quality of Service (IWQOS), pages 1-10. IEEE, 2021.","title":"Federaser: Enabling efficient client-level data removal from federated learning models","authors":"Gaoyang Liu, Xiaoqiang Ma, Yang Yang, Chen Wang, Jiangchuan Liu","year":"2021","venue":"IEEE/ACM 29th International Symposium on Quality of Service (IWQOS)","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Liu et al., 2022a] Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, and Bo Li. The right to be forgotten in feder- ated learning: An efficient realization with rapid retrain- ing. In IEEE INFOCOM 2022-IEEE Conference on Com- puter Communications, pages 1749-1758. IEEE, 2022.","title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining","authors":"Liu","year":"2022","venue":"IEEE INFOCOM 2022-IEEE Conference on Computer Communications","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Liu et al., 2022b] Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, and Bo Li. The right to be forgotten in federated learning: An efficient realization with rapid retraining. IEEE INFOCOM 2022 -IEEE Conference on Computer Communications, pages 1749-1758, 2022.","title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining","authors":"Liu","year":"2022","venue":"IEEE INFOCOM 2022 -IEEE Conference on Computer Communications","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Liu et al., 2023] Ziyao Liu, Yu Jiang, Jiyuan Shen, Minyi Peng, Kwok-Yan Lam, and Xingliang Yuan. A survey on federated unlearning: Challenges, methods, and future di- rections. arXiv preprint arXiv:2310.20448, 2023.","title":"A survey on federated unlearning: Challenges, methods, and future directions","authors":"Ziyao Liu, Yu Jiang, Jiyuan Shen, Minyi Peng, Kwok-Yan, Xingliang Lam, Yuan","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[McMahan et al., 2017] Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Ar- cas. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics, pages 1273-1282. PMLR, 2017.","title":"Communication-efficient learning of deep networks from decentralized data","authors":"Brendan Mcmahan, Eider Moore, Daniel Ramage, Seth Hampson, Blaise Aguera Y Arcas","year":"2017","venue":"Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Mercuri et al., 2022] Salvatore Mercuri, Raad Khraishi, Ramin Okhrati, Devesh Batra, Conor Hamill, Taha Ghasempour, and Andrew Nowlan. An introduction to ma- chine unlearning. arXiv preprint arXiv:2209.00939, 2022.","title":"An introduction to machine unlearning","authors":"Salvatore Mercuri, Raad Khraishi, Ramin Okhrati, Devesh Batra, Conor Hamill, Taha Ghasempour, Andrew Nowlan","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Nasr et al., 2019] Milad Nasr, Reza Shokri, and Amir Houmansadr. Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. In 2019 IEEE symposium on security and privacy (SP), pages 739-753. IEEE, 2019.","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","authors":"Milad Nasr, Reza Shokri, Amir Houmansadr","year":"2019","venue":"IEEE symposium on security and privacy (SP)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Sekhari et al., 2021] Ayush Sekhari, Jayadev Acharya, Gautam Kamath, and Ananda Theertha Suresh. Remem- ber what you want to forget: Algorithms for machine un- learning. Advances in Neural Information Processing Sys- tems, 34:18075-18086, 2021.","title":"Remember what you want to forget: Algorithms for machine unlearning","authors":"Ayush Sekhari, Jayadev Acharya, Gautam Kamath, Ananda Theertha, Suresh","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Su and Li, 2023] Ningxin Su and Baochun Li. Asyn- chronous federated unlearning. In IEEE INFOCOM 2023- IEEE Conference on Computer Communications, pages 1- 10. IEEE, 2023.","title":"Asynchronous federated unlearning","authors":"Li ; Su, Ningxin Su, Baochun Li","year":"2023","venue":"IEEE INFOCOM 2023-IEEE Conference on Computer Communications","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Sun et al., 2022] Tao Sun, Dongsheng Li, and Bao Wang. Decentralized federated averaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4289- 4301, 2022.","title":"Decentralized federated averaging","authors":"Tao Sun, Dongsheng Li, Bao Wang","year":"2022","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wang et al., 2022] Junxiao Wang, Song Guo, Xin Xie, and Heng Qi. Federated unlearning via class-discriminative pruning. In Proceedings of the ACM Web Conference 2022, pages 622-632, 2022.","title":"Federated unlearning via class-discriminative pruning","authors":"Wang","year":"2022","venue":"Proceedings of the ACM Web Conference 2022","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wu et al., 2022] Chen Wu, Sencun Zhu, and Prasenjit Mi- tra. Federated unlearning with knowledge distillation. arXiv preprint arXiv:2201.09441, 2022.","title":"Federated unlearning with knowledge distillation","authors":"Chen Wu, Sencun Zhu, Prasenjit Mitra","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yang et al., 2019] Qiang Yang, Yang Liu, Tianjian Chen, and Yongxin Tong. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2):1-19, 2019.","title":"Federated machine learning: Concept and applications","authors":"Qiang Yang, Yang Liu, Tianjian Chen, Yongxin Tong","year":"2019","venue":"ACM Transactions on Intelligent Systems and Technology (TIST)","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhang et al., 2023] Lefeng Zhang, Tianqing Zhu, Haibin Zhang, Ping Xiong, and Wanlei Zhou. Fedrecovery: Dif- ferentially private machine unlearning for federated learn- ing frameworks. IEEE Transactions on Information Foren- sics and Security, 2023.","title":"Fedrecovery: Differentially private machine unlearning for federated learning frameworks","authors":"Zhang","year":"2023","venue":"IEEE Transactions on Information Forensics and Security","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}