Technology Talk: “Securing Smart Sensing against Physical Adversarial AI Attacks”

Abstract:
Smart sensing systems using mmWave technology has promising applications in numerous scenarios, including monitoring and surveillance, healthcare, and smart home. mmWave technology is non-intrusive and can operate in situations where traditional sensors or cameras may fail. However, these systems also introduce new attack surfaces alongside their benefits. Existing security research on smart sensing systems primarily focuses on the vulnerabilities of the AI models used by these systems, without addressing the challenges of physically implementing these attacks in real-world scenarios. We identified the first physical backdoor attacks for mmWave-based HAR systems, manipulating physical signals to deceive the systems into producing targeted outputs. We will also discuss the effective countermeasures.

Bio:
Tao Li is currently an Assistant Professor in the Department of Computer and Information Technology at Purdue University. He received a Ph.D. in Computer Engineering from Arizona State University in 2020. His primary research is on security and privacy issues in AI-powered mobile sensing, wireless networks, and localization/navigation.