Cyber Security and Large-Language Models

H1-06

11.20(水) 15:30-16:10 | 展示会場内　RoomH

Thematic Seminar

Cyber Security and Large-Language Models

The astonishing performance of large-scale language models has shocked society, and AI is expected to surpass human capabilities in cyber attack response, which requires a high level of specialized skills. The U.S. Defense Advanced Research Projects Agency (DARPA) has organized the AI Cyber Challenge (AIxCC) to encourage the development of this field. In this presentation, we will introduce those latest developments and describe our investigation of the possibility of an autonomous cyber attack response system (Autonomous Cyber Reasoning System) based on a large-scale language model (LLM).

AI
Safety & Security

Speaker

Institute of Information Security

Graduate School of Information Security, Professor

Akira Otsuka

Akira Otsuka received the B.E. and the M.E. degrees from Osaka University in 1989 and 1991, respectively, and received the Ph.D. degree from the University of Tokyo in 2002. From 2005, he was with the National Institute of Advanced Industrial Science and Technology (AIST), where he was a Leader of Research Security Fundamentals from 2006 to 2010. From 2007 to 2014, he was a Visiting Professor at the Research and Development Initiative, Chuo University. He was a Visiting Researcher, Financial Research Institute, Bank of Japan (2020-2021). Since 2017, he has been a Professor with the Graduate School of Information Security, Institute of Information Security in Yokohama, Japan. He serves as a Chair of AI Safety and Security Research Group (SIG-SEC) in Japan Society of Artificial Intelligence (JSAI).

Attendee Registration