Stochastic Training for Side-Channel Resilient AI

TL;DR

This paper introduces a stochastic training approach that enhances the resilience of AI models on edge devices against side-channel attacks by using randomized configurations, achieving reduced leakage with minimal accuracy loss.

Contribution

It presents a novel training methodology that improves side-channel attack resistance without hardware modifications, suitable for existing edge AI hardware.

Findings

Reduced side-channel leakage on Google Coral Edge TPU

Maintained high model accuracy with ~1% degradation

Demonstrated robustness over 20,000 traces

Abstract

The confidentiality of trained AI models on edge devices is at risk from side-channel attacks exploiting power and electromagnetic emissions. This paper proposes a novel training methodology to enhance resilience against such threats by introducing randomized and interchangeable model configurations during inference. Experimental results on Google Coral Edge TPU show a reduction in side-channel leakage and a slower increase in t-scores over 20,000 traces, demonstrating robustness against adversarial observations. The defense maintains high accuracy, with about 1% degradation in most configurations, and requires no additional hardware or software changes, making it the only applicable solution for existing Edge TPUs.