Neuroattack: undermining spiking neural networks security through externally triggered bit-flips - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Neuroattack: undermining spiking neural networks security through externally triggered bit-flips

Résumé

Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems. More specifically, Spiking Neural Networks (SNNs) emerged as a promising solution to the accuracy, resource-utilization, and energy-efficiency challenges in machine-learning systems. While these systems are going mainstream, they have inherent security and reliability issues. In this paper, we propose NeuroAttack, a cross-layer attack that threatens the SNNs integrity by exploiting low-level reliability issues through a high-level attack. Particularly, we trigger a fault-injection based sneaky hardware backdoor through a carefully crafted adversarial input noise. Our results on Deep Neural Networks (DNNs) and SNNs show a serious integrity threat to state-of-the art machine-learning techniques.
Fichier principal
Vignette du fichier
2005.08041.pdf (1.04 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03166289 , version 1 (08-07-2022)

Identifiants

Citer

Valerio Venceslai, Alberto Marchisio, Ihsen Alouani, Maurizio Martina, Muhammad Noman Shafique. Neuroattack: undermining spiking neural networks security through externally triggered bit-flips. International Joint Conference on Neural Networks (IJCNN 2020), Jul 2020, Glasgow, United Kingdom. pp.1-8, ⟨10.1109/IJCNN48605.2020.9207351⟩. ⟨hal-03166289⟩
38 Consultations
19 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More