On Adversarial Vulnerability of PHM algorithms: An Initial Study

TL;DR

This paper explores the vulnerability of prognostics and health management (PHM) algorithms, especially those based on deep learning, to adversarial attacks using real-world time-series sensor data, highlighting a significant security concern.

Contribution

It is the first study to investigate adversarial vulnerabilities in PHM algorithms, considering unique characteristics of time-series sensor data.

Findings

PHM algorithms are vulnerable to adversarial attacks.

Real-world PHM applications demonstrate successful attack strategies.

Highlights need for robust defenses in PHM systems.

Abstract

With proliferation of deep learning (DL) applications in diverse domains, vulnerability of DL models to adversarial attacks has become an increasingly interesting research topic in the domains of Computer Vision (CV) and Natural Language Processing (NLP). DL has also been widely adopted to diverse PHM applications, where data are primarily time-series sensor measurements. While those advanced DL algorithms/models have resulted in an improved PHM algorithms' performance, the vulnerability of those PHM algorithms to adversarial attacks has not drawn much attention in the PHM community. In this paper we attempt to explore the vulnerability of PHM algorithms. More specifically, we investigate the strategies of attacking PHM algorithms by considering several unique characteristics associated with time-series sensor measurements data. We use two real-world PHM applications as examples to validate our attack strategies and to demonstrate that PHM algorithms indeed are vulnerable to adversarial attacks.