885 citations · 1.2k across the 12 of their papers we have counts for
3 papers · 1 filter
GPU-based Private Information Retrieval for On-Device Machine Learning Inference
Maximilian Lam, Jeff Johnson, Wenjie Xiong +11
On-device machine learning (ML) inference can enable the use of private user data on user devices without revealing them to remote servers. However, a pure on-device solution to pr…
Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference
Maximilian Lam, Michael Mitzenmacher, Vijay Janapa Reddi +2
Multiparty computation approaches to secure neural network inference commonly rely on garbled circuits for securely executing nonlinear activation functions. However, garbled circu…
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
Maximilian Lam, Gu-Yeon Wei, David Brooks +2
We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants give…