Laser Fault Injection in Memristor-Based Accelerators for AI/ML and Neuromorphic Computing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rahman, Muhammad Faheemur, Burleson, Wayne
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909849656229888
author Rahman, Muhammad Faheemur
Burleson, Wayne
author_facet Rahman, Muhammad Faheemur
Burleson, Wayne
contents Memristive crossbar arrays (MCA) are emerging as efficient building blocks for in-memory computing and neuromorphic hardware due to their high density and parallel analog matrix-vector multiplication capabilities. However, the physical properties of their nonvolatile memory elements introduce new attack surfaces, particularly under fault injection scenarios. This work explores Laser Fault Injection as a means of inducing analog perturbations in MCA-based architectures. We present a detailed threat model in which adversaries target memristive cells to subtly alter their physical properties or outputs using laser beams. Through HSPICE simulations of a large MCA on 45 nm CMOS tech. node, we show how laser-induced photocurrent manifests in output current distributions, enabling differential fault analysis to infer internal weights with up to 99.7% accuracy, replicate the model, and compromise computational integrity through targeted weight alterations by approximately 143%.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Laser Fault Injection in Memristor-Based Accelerators for AI/ML and Neuromorphic Computing
Rahman, Muhammad Faheemur
Burleson, Wayne
Emerging Technologies
Neural and Evolutionary Computing
Systems and Control
Memristive crossbar arrays (MCA) are emerging as efficient building blocks for in-memory computing and neuromorphic hardware due to their high density and parallel analog matrix-vector multiplication capabilities. However, the physical properties of their nonvolatile memory elements introduce new attack surfaces, particularly under fault injection scenarios. This work explores Laser Fault Injection as a means of inducing analog perturbations in MCA-based architectures. We present a detailed threat model in which adversaries target memristive cells to subtly alter their physical properties or outputs using laser beams. Through HSPICE simulations of a large MCA on 45 nm CMOS tech. node, we show how laser-induced photocurrent manifests in output current distributions, enabling differential fault analysis to infer internal weights with up to 99.7% accuracy, replicate the model, and compromise computational integrity through targeted weight alterations by approximately 143%.
title Laser Fault Injection in Memristor-Based Accelerators for AI/ML and Neuromorphic Computing
topic Emerging Technologies
Neural and Evolutionary Computing
Systems and Control
url https://arxiv.org/abs/2510.14120