Litcius/Paper detail

ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems

Jiangnan Li, Yingyuan Yang, Jinyuan Sun, Kevin Tomsovic, Hairong Qi

202158 citationsDOI

Abstract

Recent research demonstrated that the superficially well-trained machine learning (ML) models are highly vulnerable to adversarial examples. As ML techniques are becoming a popular solution for cyber-physical systems (CPSs) applications in research literatures, the security of these applications is of concern. However, current studies on adversarial machine learning (AML) mainly focus on pure cyberspace domains. The risks the adversarial examples can bring to the CPS applications have not been well investigated. In particular, due to the distributed property of data sources and the inherent physical constraints imposed by CPSs, the widely-used threat models and the state-of-the-art AML algorithms in previous cyberspace research become infeasible.

Topics & Concepts

Adversarial systemCyberspaceComputer scienceAdversarial machine learningCyber-physical systemFocus (optics)Artificial intelligenceProperty (philosophy)Computer securityMachine learningState (computer science)Data scienceThe InternetWorld Wide WebAlgorithmPhilosophyOpticsOperating systemEpistemologyPhysicsAdversarial Robustness in Machine LearningSmart Grid Security and ResilienceAdvanced Malware Detection Techniques