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

Raising Trust in the Food Supply Chain

Alexander Krumpholz, Marthie Grobler, Raj Gaire, Claire Mason, Shanae Burns (CSIRO Data61)

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 Bloomington), Xiapu Luo (Hong Kong Polytechnic University)

Read More

HERA: Hotpatching of Embedded Real-time Applications

Christian Niesler (University of Duisburg-Essen), Sebastian Surminski (University of Duisburg-Essen), Lucas Davi (University of Duisburg-Essen)

Read More

(Short) WIP: Deployability Improvement, Stealthiness User Study, and Safety...

Takami Sato, Junjie Shen, Ningfei Wang (UC Irvine), Yunhan Jia (ByteDance), Xue Lin (Northeastern University), and Qi Alfred Chen (UC Irvine)

Read More