Parasite: Mitigating Physical Side-Channel Attacks Against Neural Networks - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Parasite: Mitigating Physical Side-Channel Attacks Against Neural Networks

Résumé

Neural Networks (NNs) are now the target of various side-channel attacks whose aim is to recover the model’s parameters and/or architecture. We focus our work on EM side-channel attacks for parameter extraction. We propose a novel approach to countering such side-channel attacks, based on the method introduced by Chabanne et al. in 2021, where parasitic convolutional models are dynamically applied to the input of the victim model. We validate this new idea in the side-channel field by simulation
Fichier non déposé

Dates et versions

hal-04262861 , version 1 (27-10-2023)

Identifiants

Citer

Hervé Chabanne, Jean-Luc Danger, Linda Guiga, Ulrich Kühne. Parasite: Mitigating Physical Side-Channel Attacks Against Neural Networks. SPACE, Dec 2021, Calcutta, India, India. pp.148-167, ⟨10.1007/978-3-030-95085-9_8⟩. ⟨hal-04262861⟩
16 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More