Stefan Trawicki,

William Hackett,

Lewis Birch,

Neeraj Suri

and

Peter Garraghan

Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization (pdf, video)

Adversarial Machine Learning (AML) is a rapidly growing field of security research, with an often overlooked area being model attacks through side-channels. Previous works show such attacks to be serious threats, though little progress has been made on efficient remediation strategies that avoid costly model re-engineering. This work demonstrates a new defense against AML side channel attacks using model compilation techniques, namely tensor optimization. We show relative model attack effectiveness decreases of up to 43% using tensor optimization, discuss the implications, and direction of future work.