NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips

Authors: Valerio Venceslai, Alberto Marchisio, Ihsen Alouani, Maurizio Martina, Muhammad Shafique
Published: 2020-05-16

Source: https://arxiv.org/abs/2005.08041

PDF: https://arxiv.org/pdf/2005.08041

Labels Predicted by AI

深層学習技術 性能評価指標 機械学習手法

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

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.