Abstract
會議鏈結：https://asmeet.webex.com/asmeet/j.php?MTID=m9c0d59012a84ad114eff3ad636fb8d8a
會議號（存取碼）： 2516 860 2832
會議密碼： 9pmPMnXwk52
With the rise of Foundation Models and Generative Artificial Intelligence (AI) that can compose articles and synthesize realistic images and photos, the lines between authenticity and deception are becoming increasingly blurred in our rapidly evolving digital world. The need for advanced tools and techniques that can authenticate media contents and tell apart fake articles from real ones has never been more critical. On the other front, how best to develop powerful AI models, while keeping them efficient, robust, secure, fair, accountable, and not violating user privacy is undoubtedly important. In this talk, I will introduce developments in Digital Media Forensics and Cybersecurity that address many core problems under the umbrella of Trustworthiness of AI. For topics Digital Media Forensics, I will introduce methods for DeepFake detection, AI synthesized face detection, face spoofing detection, image manipulation detection, and multi-model article consistency analysis. I will also introduce methods that analyze articles containing infographics. For topics in AI & Cybersecurity, I will discuss adversarial methods that attack the vulnerability of AI systems as well as methods that defend against these attacks. Finally, I will introduce methods addressing privacy and security issues, including methods improving the privacy and robustness of Federated Learning, as well as secure model inference using Fully Homomorphic Encryption (FHE).
會議號（存取碼）： 2516 860 2832
會議密碼： 9pmPMnXwk52
With the rise of Foundation Models and Generative Artificial Intelligence (AI) that can compose articles and synthesize realistic images and photos, the lines between authenticity and deception are becoming increasingly blurred in our rapidly evolving digital world. The need for advanced tools and techniques that can authenticate media contents and tell apart fake articles from real ones has never been more critical. On the other front, how best to develop powerful AI models, while keeping them efficient, robust, secure, fair, accountable, and not violating user privacy is undoubtedly important. In this talk, I will introduce developments in Digital Media Forensics and Cybersecurity that address many core problems under the umbrella of Trustworthiness of AI. For topics Digital Media Forensics, I will introduce methods for DeepFake detection, AI synthesized face detection, face spoofing detection, image manipulation detection, and multi-model article consistency analysis. I will also introduce methods that analyze articles containing infographics. For topics in AI & Cybersecurity, I will discuss adversarial methods that attack the vulnerability of AI systems as well as methods that defend against these attacks. Finally, I will introduce methods addressing privacy and security issues, including methods improving the privacy and robustness of Federated Learning, as well as secure model inference using Fully Homomorphic Encryption (FHE).
Bio
Dr. Ming-Ching Chang's research has been founded by DARPA, IARPA, NIJ, VA, and GE Global Research. He has rich experience in leveraging expertise from multiple domains to accomplish multi-discipline programs and projects. He receives multiple paper awards from international conferences including IEEE MIPR 2023 Best Student Paper Award, AI City Challenge 2017 Honorary Mention Award, IEEE WACV 2012 Best Student Paper Award, and IEEE AVSS 2011 Best Paper Award - Runner-Up. He frequently serves the program chair, area chair, and referee of leading journals and conferences. He is the core organizer of the AI City Challenge, a multi-year (2017-2023) IEEE CVPR Workshops. He is the program chair of the IEEE AVSS 2019 conference and TPC chair lead of the IEEE MIPR 2022 conference. He is the Area Chair of IEEE ICIP conferences (2017, 2019-2023) and an outstanding area chair of ICME 2021 conference. He chairs the steering committee of the IEEE AVSS conference since 2022. He has authored more than 130+ peer-reviewed journal and conference publications, 7 US patents and 15 disclosures. He is a senior member of IEEE.