Biography: Kui Ren is Professor and Associate Dean of College of Computer Science and Technology at Zhejiang University, where he also directs the Institute of Cyber Science and Technology. Before that, he was SUNY Empire Innovation Professor at State University of New York at Buffalo, USA. He received his PhD degree in Electrical and Computer Engineering from Worcester Polytechnic Institute. Kui’s current research interests include Data Security, IoT Security, AI Security, and Privacy. He received many recognitions including Guohua Distinguished Scholar Award of ZJU, IEEE CISTC Technical Recognition Award, SUNY Chancellor’s Research Excellence Award, Sigma Xi Research Excellence Award, NSF CAREER Award, etc. Kui has published extensively in peer-reviewed journals and conferences and received the Test-of-time Paper Award from IEEE INFOCOM and many Best Paper Awards, including ACM MobiSys, IEEE ICDCS, IEEE ICNP, IEEE Globecom, ACM/IEEE IWQoS, etc. His h-index is 89, with a total citation exceeding 44,000 according to Google Scholar. Kui is a Fellow of ACM and IEEE. He is a frequent reviewer for funding agencies internationally and serves on the editorial boards of many IEEE and ACM journals. Among others, he currently serves as Chair of SIGSAC of ACM China Council, a member of ACM ASIACCS steering committee, and a member of S&T Committee of Ministry of Education of China.
Title：security and privacy in intelligent voice systems
Integrating AI and IoT technologies has endowed intelligent voice systems with powerful cognition capabilities and natural interaction experience. Behind the bright prospect of AIoT-enabled intelligent voice systems, the shadow of security and privacy threats is also enlarged due to the endogenous vulnerability of AI and the natural openness of IoT.
This talk explores the frontiers of security and privacy issues in intelligent voice systems, covering real-world malicious injections and non-intrusive speech sanitization. The malicious injections emit side-channel magnetic signals for stealthy command activation, and even directly deliver acoustic perturbations for real-time speaker impersonation. The speech sanitization is also highlighted, exploring the use of inconspicuous ultrasound and adversarial perturbation designed to obfuscate linguistic content and voiceprint, ensuring privacy-preserving speech communication.
In this talk, we will elaborate on advancements in this field and report the latest results of our team. We will delve into the security and privacy issues of intelligent voice systems and their role in facilitating the trustworthy and sustainable development of AIoT.