Practical Secure Aggregation for Privacy-Preserving Machine Learning
Keith Bonawitz, Vladimir Ivanov, Ben Kreuter et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 2017
We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner (i.e. without learning each user's individual contribution), and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and active adversary settings, and show that security is maintained even if an arbitrarily chosen subset of users drop out at any time. We evaluate the efficiency of our protocol and show, by complexity analysis and a concrete implementation, that its runtime and communication overhead remain low even on large data sets and client pools. For 16-bit input values, our protocol offers $1.73 x communication expansion for 210 users and 220-dimensional vectors, and 1.98 x expansion for 214 users and 224-dimensional vectors over sending data in the clear.
Cited by 3,752 works. doi:10.1145/3133956.3133982
Authors
References
- New directions in cryptography
- How to share a secret
- How to Generate Cryptographically Strong Sequences of Pseudorandom Bits
- Theory and application of trapdoor functions
- How to play ANY mental game
- Deep Learning
- Theory and application of trapdoor functions
- Completeness theorems for non-cryptographic fault-tolerant distributed computation
- Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data