Research Seminar by Dr. Qun SONG from TU Delft

Time: 1:30pm-2:45pm, June 12th Wednesday 2024

Venue: CCDS Meeting Room (N4-02a-35)

Title: Towards Resilient Autonomous Cyber-Physical Systems against Adversarial Examples

Abstract: Deep learning is shown to be susceptible to adversarial examples, which are crafted inputs aiming to cause wrong classification outputs for deep models by adding minute perturbations on the clean inputs. Thus, deploying deep learning models on safety-critical cyber-physical systems without incorporating effective countermeasures against adversarial examples raises security concerns. This talk is about the studies on the threat and countermeasures for the adversarial example attack as an ongoing concern for the safety-critical autonomous cyber-physical systems. This talk will introduce the dynamic ensemble-based defenses designed under the strategy of moving target defense that effectively counteract the adaptive adversarial example adversary for embedded deep visual sensing. This talk will also present the systematic requirement investigation and credibility analysis of adversarial example attack against the power grid voltage stability assessment and effective countermeasure.

Biography: Qun Song received Ph.D. from Nanyang Technological University, Singapore and B.Eng. from Nankai University, China. She is currently an Assistant Professor in the Embedded Systems Group of the Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) at Delft University of Technology, the Netherlands. Her research interests include the Internet of Things, cyber-physical systems, artificial intelligence, and security for autonomous driving. She is the recipient of the 2023 MobiCom Best Community Contribution Award, 2022 SenSys Best Paper Award Finalist, the 2021 IPSN Best Artifact Award Runner-up, and NTU SCALE Best Demo Award.

Host: Rui Tan