Adversarial Attacks on Machine Learning in Embedded and IoT Platforms
This addresses security vulnerabilities in widely used embedded and IoT platforms, but it is incremental as it reviews existing research rather than presenting new findings.
The paper examines how model compression techniques for deploying machine learning on resource-limited embedded and IoT systems affect adversarial robustness, providing an overview of attacks, compression methods, and their interplay.
Machine learning (ML) algorithms are increasingly being integrated into embedded and IoT systems that surround us, and they are vulnerable to adversarial attacks. The deployment of these ML algorithms on resource-limited embedded platforms also requires the use of model compression techniques. The impact of such model compression techniques on adversarial robustness in ML is an important and emerging area of research. This article provides an overview of the landscape of adversarial attacks and ML model compression techniques relevant to embedded systems. We then describe efforts that seek to understand the relationship between adversarial attacks and ML model compression before discussing open problems in this area.