Sinem Sav (EPFL), Apostolos Pyrgelis (EPFL), Juan Ramón Troncoso-Pastoriza (EPFL), David Froelicher (EPFL), Jean-Philippe Bossuat (EPFL), Joao Sa Sousa (EPFL), Jean-Pierre Hubaux (EPFL)

In this paper, we address the problem of privacy-preserving training and evaluation of neural networks in an $N$-party, federated learning setting. We propose a novel system, POSEIDON, the first of its kind in the regime of privacy-preserving neural network training. It employs multiparty lattice-based cryptography to preserve the confidentiality of the training data, the model, and the evaluation data, under a passive-adversary model and collusions between up to $N-1$ parties. To efficiently execute the secure backpropagation algorithm for training neural networks, we provide a generic packing approach that enables Single Instruction, Multiple Data (SIMD) operations on encrypted data. We also introduce arbitrary linear transformations within the cryptographic bootstrapping operation, optimizing the costly cryptographic computations over the parties, and we define a constrained optimization problem for choosing the cryptographic parameters. Our experimental results show that POSEIDON achieves accuracy similar to centralized or decentralized non-private approaches and that its computation and communication overhead scales linearly with the number of parties. POSEIDON trains a 3-layer neural network on the MNIST dataset with 784 features and 60K samples distributed among 10 parties in less than 2 hours.

View More Papers

What Remains Uncaught?: Characterizing Sparsely Detected Malicious URLs on...

Sayak Saha Roy, Unique Karanjit, Shirin Nilizadeh (The University of Texas at Arlington)

Read More

As Strong As Its Weakest Link: How to Break...

Kai Li (Syracuse University), Jiaqi Chen (Syracuse University), Xianghong Liu (Syracuse University), Yuzhe Tang (Syracuse University), XiaoFeng Wang (Indiana University...

Read More

CROW: Code Diversification for WebAssembly

Javier Cabrera Arteaga, Orestis Floros, Benoit Baudry, Martin Monperrus (KTH Royal Institute of Technology), Oscar Vera Perez (Univ Rennes, Inria,...

Read More

TASE: Reducing Latency of Symbolic Execution with Transactional Memory

Adam Humphries (University of North Carolina), Kartik Cating-Subramanian (University of Colorado), Michael K. Reiter (Duke University)

Read More