← Search

Maximilian Lam

2 accepted papers

2021

Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix

ICML 2021oral

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 given repeated observations, enabling the server to recover privileged information about individual users’ private training…

2016

Cyclades: Conflict-free Asynchronous Machine Learning

NeurIPS 2016poster

We present Cyclades, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting. Cyclades is asynchronous during model updates, and requires no memory locking mechanisms, similar to Hogwild!-type algorithms. Unlike Hogwild!, Cyclades introduces no conflicts d…