AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning enables users to collaboratively train a machine learning model over their private datasets. Secure aggregation protocols are employed to mitigate information leakage about the local datasets. This setup, however, still leaks the participation of a user in a training iteration, which can also be sensitive. Protecting user anonymity is even more challenging in dynamic environments where users may (re)join or leave the training process at any point of time. In this paper, we introduce AnoFel, the first framework to support private and anonymous dynamic participation in federated learning. AnoFel leverages several cryptographic primitives, the concept of anonymity sets, differential privacy, and a public bulletin board to support anonymous user registration, as well as unlinkable and confidential model updates submission. Additionally, our system allows dynamic participation, where users can join or leave at any time, without needing any recovery protocol or interaction. To assess security, we formalize a notion for privacy and anonymity in federated learning, and formally prove that AnoFel satisfies this notion. To the best of our knowledge, our system is the first solution with provable anonymity guarantees. To assess efficiency, we provide a concrete implementation of AnoFel, and conduct experiments showing its ability to support learning applications scaling to a large number of clients. For an MNIST classification task with 512 clients, the client setup takes less than 3 sec, and a training iteration can be finished in 3.2 sec. We also compare our system with prior work and demonstrate its practicality for contemporary learning tasks.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 97 references that are in the map. First posted on arXiv 12 Jun 2023.
Builds on
34 of 97 references.
References · 34
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2016Deep Learning with Differential Privacycited by 2,728
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
- 2018Group Normalizationcited by 1,524
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
- 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
- 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 231
- 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
- 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
22 more
- 2017Revisiting Distributed Synchronous SGDcited by 142
- 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
- 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
- 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
- 2021Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learningcited by 86
- 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
- 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
- 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 61
- 2020Improving Robustness to Model Inversion Attacks via Mutual Information Regularizationcited by 52
- 2019HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learningcited by 51
- 2020Investigating Membership Inference Attacks under Data Dependenciescited by 32
- 2021EIFFeL: Ensuring Integrity for Federated Learningcited by 28
- 2021RoFL: Robustness of Secure Federated Learningcited by 25
- 2020On the Effectiveness of Regularization Against Membership Inference Attackscited by 24
- 2020ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharingcited by 20
- 2020Private Wireless Federated Learning with Anonymous Over-the-Air Computationcited by 16
- 2020A bounded-noise mechanism for differential privacycited by 15
- 2020Anonymizing Data for Privacy-Preserving Federated Learningcited by 8
- 2021FRL: Federated Rank Learningcited by 8
- 2022zPROBE: Zero Peek Robustness Checks for Federated Learningcited by 6
- 2021Secure and Privacy-Preserving Federated Learning via Co-Utilitycited by 5
- 2016Enhancing Bitcoin Security and Performance with Strong Consistency via Collective Signingcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.