Evaluation of parameter-based attacks against embedded neural networks with laser injection - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Evaluation of parameter-based attacks against embedded neural networks with laser injection

Résumé

Machine Learning models are exposed to numerous attack vectors that threaten the confidentiality, integrity and availability of many AI-based systems. These security concerns urge the development of practical robustness evaluation methods to help ongoing and future standardization and certification actions. Models embed in physically accessible devices are critical cases since their attack surface also encompasses physical threats such as fault injection attacks. More particularly, parameter-based attacks (such as the Bit-Flip Attack, BFA) highlight the lack of robustness of state-of-the-art deep neural network models when confronted by accurate and optimal alterations of their parameters stored in memory. This work goes beyond simulation-based evaluation by demonstrating, for the first time, a complete BFA-like attack on a 32-bit Cortex-M microcontroller thanks to laser injection, a standard fault injection means for security evaluation, that enables spatially and temporally accurate faults. We show a high consistency between simulation and experimental attacks with only a few bit-sets necessary to significantly alter the performance of a standard neural network model.
Fichier principal
Vignette du fichier
SafeComp_2023.pdf (585.72 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

cea-04607994 , version 1 (11-06-2024)

Identifiants

Citer

Mathieu Dumont, Kévin Hector, Pierre-Alain Moellic, Jean-Max Dutertre, Simon Pontie. Evaluation of parameter-based attacks against embedded neural networks with laser injection. SAFECOMP 2023 - 21st Smart Card Research and Advanced Application Conference, Université de Toulouse, Sep 2023, Toulouse, France. pp.259-272, ⟨10.1007/978-3-031-40923-3_19⟩. ⟨cea-04607994⟩
24 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More