11月9日，“上海人工智能实验室学术论坛”将举办第21期“星河Talk”。本期邀请IBM托马斯沃森研究中心（IBM Thomas J. Watson Research Center）主任研究科学家Pin-yu Chen，带来主题报告Exploring Safety Risks in Large Language Models and Generative AI。“星河Talk”不定期邀请全球顶尖学者，分享学术成果、探讨科技前沿。

“星河Talk”第21期

【活动详情】

主题：Exploring Safety Risks in Large Language Models and Generative AI

嘉宾：Pin-yu Chen  Principal Research Scientist at IBM Thomas J. Watson Research Center

时间：北京时间 11月9日 上午10:00-11:00

参与方式：视频号直播

【讲座简介】

Large language models (LLMs) and Generative AI (GenAI) are at the forefront of current AI research and technology. With their rapidly increasing popularity and availability, challenges and concerns about their misuse and safety risks are becoming more prominent than ever. In this talk, the speaker will provide new tools and insights to explore the safety and robustness risks associated with state-of-the-art LLMs and GenAI models. In particular, the speaker will cover (i) safety risks in fine-tuning LLMs, (ii) backdoor analysis of text-to-image diffusion models, (iii) prompt engineering for safety debugging, and (iv) robust detection of AI-generated text from LLMs.

【本期嘉宾】

Pin-Yu Chen

Principal Research Scientist

IBM Thomas J. Watson Resarch Center

Dr. Pin-Yu Chen is a principal research scientist at IBM Thomas J. Watson Research Center in Yorktown Heights, NY, USA. He also serves as the chief scientist of RPI-IBM AI Research Collaboration and is the principal investigator of ongoing MIT-IBM Watson AI Lab projects. Dr. Chen earned his Ph.D. in electrical engineering and computer science from the University of Michigan, Ann Arbor, USA, in 2016. His recent research focuses on adversarial machine learning of neural networks for robustness and safety. His long-term research vision is to build trustworthy machine learning systems. In 2023, he was honored with the IJCAI Computers and Thought Award. He is also a co-author of the book Adversarial Robustness for Machine Learning.

During his tenure at IBM Research, Dr. Chen has received several research accomplishment awards, including IBM Master Inventor, IBM Corporate Technical Award, and IBM Pat Goldberg Memorial Best Paper. He has made significant contributions to IBM's open-source libraries, including the Adversarial Robustness Toolbox (ART 360) and AI Explainability 360 (AIX 360). Dr. Chen has authored more than 50 papers related to trustworthy machine learning, which have been presented at major AI and machine learning conferences. He has also conducted tutorials at conferences like NeurIPS’22, AAAI(’22,’23), IJCAI’21, CVPR(’20,’21,’23), ECCV’20, ICASSP(’20,’22,’23), KDD’19, and Big Data’18. Additionally, he has organized several workshops on adversarial machine learning.

Currently, Dr. Chen serves on the editorial board of Transactions on Machine Learning Research and acts as an Area Chair or Senior Program Committee member for conferences such as NeurIPS, ICML, AAAI, IJCAI, and PAKDD. He has received prestigious awards, including the IEEE GLOBECOM 2010 GOLD Best Paper Award and the UAI 2022 Best Paper Runner-Up Award.

上海人工智能实验室学术论坛

“上海人工智能实验室学术论坛”分设“星河Talk”与“星启Talk”两个主题系列活动，将分别邀请全球顶尖教授和杰出青年学者作为嘉宾，线上线下分享学术成果、探讨科技前沿。更多精彩内容，敬请期待。