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

Demo #5: Securing Heavy Vehicle Diagnostics

Jeremy Daily, David Nnaji, and Ben Ettlinger (Colorado State University)

Read More

Ovid: Message-based Automatic Contact Tracing

Leonie Reichert and Samuel Brack (Humboldt University of Berlin); Björn Scheuermann (Humboldt-University of Berlin)

Read More

SymQEMU: Compilation-based symbolic execution for binaries

Sebastian Poeplau (EURECOM and Code Intelligence), Aurélien Francillon (EURECOM)

Read More

icLibFuzzer: Isolated-context libFuzzer for Improving Fuzzer Comparability

Yu-Chuan Liang, Hsu-Chun Hsiao (National Taiwan University)

Read More