A practical introduction to side-channel extraction of Deep Neural Network parameters - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

A practical introduction to side-channel extraction of Deep Neural Network parameters

Abstract

Model extraction is a major threat for embedded deep neural network models that leverages an extended attack surface. Indeed, by physically accessing a device, an adversary may exploit side-channel leakages to extract critical information of a model (i.e., its architecture or internal parameters). Different adversarial objectives are possible including a fidelity-based scenario where the architecture and parameters are precisely extracted (model cloning). We focus this work on software implementation of deep neural networks embedded in a high-end 32-bit microcontroller (Cortex-M7) and expose several challenges related to fidelity-based parameters extraction through side-channel analysis, from the basic multiplication operation to the feed-forward connection through the layers. To precisely extract the value of parameters represented in the single-precision floating point IEEE-754 standard, we propose an iterative process that is evaluated with both simulations and traces from a Cortex-M7 target. To our knowledge, this work is the first to target such an high-end 32-bit platform. Importantly, we raise and discuss remaining challenges for the complete extraction of a deep neural network model, more particularly the critical case of biases.
Fichier principal
Vignette du fichier
2211.05590v1.pdf (538.67 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

cea-04038159 , version 1 (27-06-2024)

Identifiers

Cite

Raphaël Joud, Pierre-Alain Moëllic, Simon Pontie, Jean-Baptiste Rigaud. A practical introduction to side-channel extraction of Deep Neural Network parameters. CARDIS 2022 - 21st Smart Card Research and Advanced Application Conference, University of Birmingham, Nov 2022, Birmingham (UK), United Kingdom. pp.45-65, ⟨10.1007/978-3-031-25319-5_3⟩. ⟨cea-04038159⟩
103 View
8 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More