Like an open book ? Read neural network architecture with simple power analysis on 32-bit microcontrollers - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Conference Papers Year : 2023

Like an open book ? Read neural network architecture with simple power analysis on 32-bit microcontrollers

Abstract

Model extraction is a growing concern for the security of AI systems. For deep neural network models, the architecture is the most important information an adversary aims to recover. Being a sequence of repeated computation blocks, neural network models deployed on edge-devices will generate distinctive side-channel leakages. The latter can be exploited to extract critical information when targeted platforms are physically accessible. By combining theoretical knowledge about deep learning practices and analysis of a widespread implementation library (ARM CMSIS-NN), our purpose is to answer this critical question: how far can we extract architecture information by simply examining an EM side-channel trace? For the first time, we propose an extraction methodology for traditional MLP and CNN models running on a high-end 32-bit microcontroller (Cortex-M7) that relies only on simple pattern recognition analysis. Despite few challenging cases, we claim that, contrary to parameters extraction, the complexity of the attack is relatively low and we highlight the urgent need for practicable protections that could fit the strong memory and latency requirements of such platforms.
Fichier principal
Vignette du fichier
CARDIS_2023__Architecture_Extraction.pdf (2.56 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

cea-04607993 , version 1 (11-06-2024)

Identifiers

Cite

Raphaël Joud, Pierre-Alain Moellic, Simon Pontie, Jean-Baptiste Rigaud. Like an open book ? Read neural network architecture with simple power analysis on 32-bit microcontrollers. CARDIS 2023 - 22nd Smart Card Research and Advanced Application Conference, Nov 2023, Amsterdam, Netherlands. pp.256-276, ⟨10.1007/978-3-031-54409-5_13⟩. ⟨cea-04607993⟩
0 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More