Fault Injection on Embedded Neural Networks: Impact of a Single Instruction Skip - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Conference Papers Year : 2023

Fault Injection on Embedded Neural Networks: Impact of a Single Instruction Skip

Abstract

With the large-scale integration and use of neural network models, especially in critical embedded systems, their security assessment to guarantee their reliability is becoming an urgent need. More particularly, models deployed in embedded platforms, such as 32-bit microcontrollers, are physically accessible by adversaries and therefore vulnerable to hardware disturbances. We present the first set of experiments on the use of two fault injection means, electromagnetic and laser injections, applied on neural networks models embedded on a Cortex M4 32-bit microcontroller platform. Contrary to most of state-of-the-art works dedicated to the alteration of the internal parameters or input values, our goal is to simulate and experimentally demonstrate the impact of a specific fault model that is instruction skip. For that purpose, we assessed several modification attacks on the control flow of a neural network inference. We reveal integrity threats by targeting several steps in the inference program of typical convolutional neural network models, which may be exploited by an attacker to alter the predictions of the target models with different adversarial goals.
Fichier principal
Vignette du fichier
DSD2023_MOELLIC_CEA.pdf (2.73 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

cea-04607936 , version 1 (11-06-2024)

Identifiers

Cite

Clément Gaine, Pierre-Alain Moellic, Olivier Potin, Jean-Max Dutertre. Fault Injection on Embedded Neural Networks: Impact of a Single Instruction Skip. DSD/SEAA 2023 - 26th Euromicro Conference Series on Digital System Design and 49th Euromicro Conference Series on Software Engineering and Advanced Applications, Sep 2023, Durres, Albania. pp.317-324, ⟨10.1109/DSD60849.2023.00052⟩. ⟨cea-04607936⟩
0 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More