AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learning
It addresses privacy concerns for users in federated learning by ensuring anonymity, which is crucial for sensitive applications, though it builds incrementally on existing cryptographic and differential privacy techniques.
The paper tackles the problem of user anonymity in federated learning, especially in dynamic environments where users can join or leave, by introducing AnoFel, a framework that supports private and anonymous participation with provable guarantees, achieving client setup in less than 3 seconds and training iterations in 3.2 seconds for 512 clients on an MNIST task.
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.