Call for Participation
In 2022, the Japan Society of Artificial Intelligence (JSAI) established a Special Interest Group on AI Safety and Security (SIG-SEC). SIG-SEC aims to foster a research community comprising experts in AI and Information Security to lead the interdisciplinary research field of “AI Safety and Security” or so-called “Trustworthy AI.”
In recent years, numerous products and services utilizing AI technology have permeated society, with AI-driven decision-making increasingly exerting influence over human lives and various industries. As AI-driven autonomous decision-making gradually displaces human involvement, the necessity to consider AI security as a design principle has grown significantly. This symposium aims to explore and advance research in the realm of AI safety and security, encompassing topics such as malfunction, attacks, defenses, tracking, and analysis, in pursuit of innovative ideas and solutions.
We welcome Professor Shamir for the 1st International Symposium on AI Safety and Security. We look forward to your participation!
Orgnaizer
Co-organizer
Supported by
Sponsored by
JSAI SIG-SEC (Japan Society of Artificial Intelligence, AI Safety and Security Special Interest Group)
AWS (AI Security Workshop Committee)
JDC (Japan Datacom), IISEC(Institute of Information Security)
DNV Business Assurance Japan
Date
Venue
Registration URL
Jan 15th (Mon), 2024
Institute of Information Security (IISEC)
2-14-1 Tsuruyacho, Kanagawa-ku, Yokohama 221-0835, Japan
https://www.iisec.ac.jp/english/access/
(5 min walk from JR Yokohama Station)
https://www.ai-gakkai.or.jp/sig-system/sigusers/add/sec/int_sigsec2024
Program
| 13:30-13:35 | Opening |
| 13:35-13:45 | Introduction of Heidelberg Laureate Forum Yuko Ishida (Japan Datacom) |
| 13:45-14:45 | Invited Talk (Tentative) The Dimpled Manifold Model of Adversarial Examples in Machine Learning Adi Shamir, Odelia Melamed, Oriel BenShmuel |
| 14:45-15:00 | Break |
| 15:00-15:50 Session 1 | Robustness bounds on the successful adversarial examples: Theory and Practice Hiroaki Maeshima, Akira Otsuka(Institute of Information Security) Learning on Contextual Code Property Graph for Source Code Vulnerability Detection Muhammad Fakhrur Rozi, Seiichi Ozawa (Kobe University) |
| 15:50-16:00 | Break |
| 16:00-16:50 Session 2 | AI-generated text detection method using entropy with text frequency Kaito Taguchi, Yujie Gu, Kouichi Sakurai(Kyushu University) Re-visited Privacy-Preserving Machine Learning Atsuko Miyaji, Tatuhiro Yamatsuki, Bingchang He, and Shintaro Yamashita (Osaka University) |
| 16:50 | Closing |
大塚研究室 