报告标题：Securing AI System from A Lifecycle Perspective
报告时间：12月18日13：30
报告地点：理科大楼B1002
报告摘要： As artificial intelligence systems become embedded in critical domains, from healthcare and finance to autonomous systems and national infrastructure, securing them is no longer optional. This talk examines the full AI security lifecycle, revealing vulnerabilities that emerge during data collection, model development, training, and deployment. We will explore cutting-edge adversarial threats, data poisoning, and model extraction attacks that challenge trust in AI, and discuss state-of-the-art defenses such as robust training, privacy-preserving learning, and secure deployment pipelines. The talk will also highlight the accountability of AI code generators, offering a research-oriented perspective on ensuring transparency and reliability across the entire AI system lifecycle. By adopting this holistic, lifecycle-driven approach, we can better safeguard AI systems, keep them aligned with human values, and inspire the next generation of research in trustworthy and resilient AI. Professor Yang Xiang received his PhD in Computer Science from Deakin University, Australia. He is currently a full professor and the Director of Digital Capability Research Platform, Swinburne University of Technology, Australia. In the past 20 years, he has been working in the broad area of Cybersecurity, which covers software, system, network, and application security. He has published more than 300 research papers in many international conferences and journals in Cybersecurity, such as ACM CCS, IEEE S&P, Usenix Security, NDSS, IEEE TDSC, and IEEE TIFS. He is the Editor-in-Chief of the SpringerBriefs on Cyber Security Systems and Networks. He serves as the Associate Editor of the ACM Computing Surveys. He served as the Associate Editor of IEEE Transactions on Dependable and Secure Computing, IEEE Internet of Things Journal, IEEE Transactions on Computers, and IEEE Transactions on Parallel and Distributed Systems. He is a current member of College of Experts (CoE) of the Australian Research Council (ARC). He is a Fellow of the IEEE.