Topic: Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts

Speaker: Prof. Dr.-Ing. Wei-Chen Chiu, Computer Science, National Chiao Tung University

Time: 2023.9.5 (Tue) 14:00-16:00

Venue: CGU Artificial Intelligence Research Center (Management Building 11F)

Join Online: https://shorturl.at/wyKO9

About the Speaker:

Prof. Dr.-Ing. Wei-Chen Chiu received the B.S. degree in Electrical Engineering & Computer Science and the M.S. degree in Computer Science from National Chiao Tung University (Hsinchu, Taiwan) in 2008 and 2009 respectively. He further received Doctor of Engineering Science (Dr.-Ing.) from Max Planck Institute for Informatics (Saarbrûcken, Germany) in 2016. He joined Department of Computer Science, National Chiao Tung University as an Assistant Professor from August 2017 and got promoted to Associate Professor in July 2020. From May 2021, he was also hired as a Joint Appointment Research Fellow by the Mechanical and Mechatronics Systems Lab of Industrial Technology Research Institute, Taiwan. His current research interests generally include computer vision, machine learning, and image processing, with special focuses on generative models, multi-modal perception, and 3D recognition.

Talk Abstract:

Text-to-image diffusion models lately have shown remarkable ability in high-quality content generation, and become one of the representatives for the recent wave of transformative AI. Nevertheless, such advance comes with an intensifying concern about the misuse of this generative technology, especially for producing copyrighted or NSFW (i.e. not safe for work) images. Although efforts have been made to filter inappropriate images/prompts or remove undesirable concepts/styles via model fine-tuning, the reliability of these safety mechanisms against diversified problematic prompts remains largely unexplored. In this talk, I will give an introduction for debugging and red-teaming tool proposed by my research group recently, which automatically finds problematic prompts for diffusion models to test the reliability of a deployed safety mechanism. The overview of other recent research findings in my group will also be covered if time allows.

Organizers: College of Intelligent Computing & Artificial Intelligence Research Center

※ No registration needed.