Date：2025/8/19 17:20
Location：R326, CSIE
Speakers：Dr. Ming-Ching Chang
Host：傅楸善教授
Abstract:
Trustworthy AI research aims to create AI models that are efficient, robust, secure, fair, privacy-preserving, and accountable. As the adoption of Foundation Models and Generative AI grows, enabling the composition of articles and the generation of hyper-realistic images, the boundary between authenticity and deception is increasingly blurred in our rapidly evolving digital landscape. The demand for sophisticated tools and techniques to authenticate media content and discern the real from the fake has never been more urgent.
In this talk, I will explore recent breakthroughs in Trustworthy AI, Digital Media Forensics, and secure computation. First, I will introduce a novel approach to learning multi-manifold embeddings for Out-of-Distribution (OOD) detection, along with a method for uncovering hidden hallucination factors in large vision-language models through causal analysis. Additionally, I will cover a noisy-label learning technique designed to tackle long-tailed data distributions.
In the field of Digital Media Forensics, I will showcase novel advancements in Image Manipulation Detection (IMD) using implicit neural representations under limited supervision. This includes the development of IMD datasets featuring object-awareness and semantically significant annotations, leveraging stable diffusion to emulate real-world scenarios more effectively.
Finally, I will discuss key innovations in secure encrypted computation, particularly in accelerating Fully Homomorphic Encryption (FHE) for deep neural network inference using GPUs, as well as enhancing functional bootstrapping through quantization and network fine-tuning strategies.
In this talk, I will explore recent breakthroughs in Trustworthy AI, Digital Media Forensics, and secure computation. First, I will introduce a novel approach to learning multi-manifold embeddings for Out-of-Distribution (OOD) detection, along with a method for uncovering hidden hallucination factors in large vision-language models through causal analysis. Additionally, I will cover a noisy-label learning technique designed to tackle long-tailed data distributions.
In the field of Digital Media Forensics, I will showcase novel advancements in Image Manipulation Detection (IMD) using implicit neural representations under limited supervision. This includes the development of IMD datasets featuring object-awareness and semantically significant annotations, leveraging stable diffusion to emulate real-world scenarios more effectively.
Finally, I will discuss key innovations in secure encrypted computation, particularly in accelerating Fully Homomorphic Encryption (FHE) for deep neural network inference using GPUs, as well as enhancing functional bootstrapping through quantization and network fine-tuning strategies.
Biography:
Dr. Ming-Ching Chang is an Associate Professor & Co-Director of the CVML Lab., Dept. of Computer Science, College of Nanotechnology, Science, and Engineering (CNSE) at University at Albany, State University of New York (SUNY). His research has been founded by DARPA, IARPA, NIJ, VA, GE Global Research, and Inventec Corp. 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 the ECCV 2024 Beyond Enclidean Hyperbolic and Hyperspherical Learning for Computer Vision Workshop Best Paper Award, the IEEE MIPR 2023 Best Student Paper Award, AI City Challenge 2017 Honorary Mention Award, the IEEE WACV 2012 Best Student Paper Award, and the IEEE AVSS 2011 Best Paper Award - Runner-Up. He is the Associate Editor of the IEEE Trans. on Multimedia journal since 2024. He frequently serves as 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 serves as Program Co-Chair of the IEEE ICME 2025 conference, General Chair (2025) and Program Chair (2024 and 2019) of the IEEE AVSS conference, and General Chair (2024) and TPC Chair Lead (2022) of the IEEE MIPR conference. He is the Area Chair of the IEEE ICIP conferences (2017, 2019-2025) and an outstanding Area Chair of the ICME 2021 conference. He chairs the steering committee of the IEEE AVSS conference since 2022. He has authored more than 167+ peer-reviewed journal and conference publications, 7 US patents and 15 disclosures. He is a senior member of IEEE.