Enhancing Adversarial Attacks on Single-Layer NVM Crossbar-Based Neural Networks with Power Consumption Information

TL;DR

This paper demonstrates that power consumption data from NVM crossbar hardware can enhance adversarial attack strategies on single-layer neural networks, revealing vulnerabilities and improving attack efficiency.

Contribution

It introduces the novel use of power consumption information to improve adversarial attacks on crossbar-based neural networks, highlighting a new security concern.

Findings

Power consumption reveals neural network weight information.

Power data improves black box attack efficiency.

Experimental results on MNIST and CIFAR-10 datasets.

Abstract

Adversarial attacks on state-of-the-art machine learning models pose a significant threat to the safety and security of mission-critical autonomous systems. This paper considers the additional vulnerability of machine learning models when attackers can measure the power consumption of their underlying hardware platform. In particular, we explore the utility of power consumption information for adversarial attacks on non-volatile memory crossbar-based single-layer neural networks. Our results from experiments with MNIST and CIFAR-10 datasets show that power consumption can reveal important information about the neural network's weight matrix, such as the 1-norm of its columns. That information can be used to infer the sensitivity of the network's loss with respect to different inputs. We also find that surrogate-based black box attacks that utilize crossbar power information can lead to improved attack efficiency.