Stochastic Training for Side-Channel Resilient AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dubey, Anuj, Aysu, Aydin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915331924033536
author Dubey, Anuj
Aysu, Aydin
author_facet Dubey, Anuj
Aysu, Aydin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stochastic Training for Side-Channel Resilient AI
Dubey, Anuj
Aysu, Aydin
Cryptography and Security
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.
title Stochastic Training for Side-Channel Resilient AI
topic Cryptography and Security
url https://arxiv.org/abs/2506.06597