Saved in:
Bibliographic Details
Main Authors: Heidary, Masoud, Joardar, Biresh Kumar
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.27439
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914429825712128
author Heidary, Masoud
Joardar, Biresh Kumar
author_facet Heidary, Masoud
Joardar, Biresh Kumar
contents The dependability of AI models relies largely on the reliability of the underlying computation hardware. Hardware aging attacks can compromise the computing substrate and disrupt AI models over the long run. In this work, we present a new hardware aging attack that exploits commutative properties of addition to disrupt the multiply-and-add operation that forms the backbone of almost all AI models. By permuting the inputs of an adder, the attack preserves functional correctness while inducing unbalanced stress among transistors, accelerating delay degradation in the circuit. Unlike prior approaches that rely on input manipulation, additional trojan circuitry, etc., the proposed method incurs virtually no area or software overhead. Experimental results with two types of multipliers, different bit widths, a mix of AI models and datasets demonstrates that the proposed attack degrades inference accuracy by up to 64% in 4 years, posing a significant threat to AI accelerators. The attack can also be extended to arithmetic units of general-purpose processors.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27439
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Attacking AI Accelerators by Leveraging Arithmetic Properties of Addition
Heidary, Masoud
Joardar, Biresh Kumar
Cryptography and Security
Hardware Architecture
The dependability of AI models relies largely on the reliability of the underlying computation hardware. Hardware aging attacks can compromise the computing substrate and disrupt AI models over the long run. In this work, we present a new hardware aging attack that exploits commutative properties of addition to disrupt the multiply-and-add operation that forms the backbone of almost all AI models. By permuting the inputs of an adder, the attack preserves functional correctness while inducing unbalanced stress among transistors, accelerating delay degradation in the circuit. Unlike prior approaches that rely on input manipulation, additional trojan circuitry, etc., the proposed method incurs virtually no area or software overhead. Experimental results with two types of multipliers, different bit widths, a mix of AI models and datasets demonstrates that the proposed attack degrades inference accuracy by up to 64% in 4 years, posing a significant threat to AI accelerators. The attack can also be extended to arithmetic units of general-purpose processors.
title Attacking AI Accelerators by Leveraging Arithmetic Properties of Addition
topic Cryptography and Security
Hardware Architecture
url https://arxiv.org/abs/2603.27439