閉じる

PHYSICAL AI
SECURITY
PROJECT

SCROLL

We develop security technologies that protect physical AI (AI-driven cyber-physical systems such as autonomous vehicles) from adversarial attacks and ensure their safety. By uncovering the threats that adversarial inputs pose to sensors, cameras, AI models, control mechanisms, and onboard computers, and building end-to-end resilience against them, we pave the way for the safe deployment of physical AI in society. Our project is part of the JST CREST research area "Creation of System Software for Society 5.0 by Integrating Fundamental Theories and System Platform Technologies".

MEMBER

Our team brings together researchers with complementary expertise in security, AI, hardware and sensing, control, and system software. Going beyond the individual components of physical AI systems such as autonomous vehicles (sensors, cameras, AI models, control mechanisms, and onboard computers), we study the entire end-to-end system that integrates them, combining theory, application, and implementation in a broad research approach.

CONTACT

CONTACT /
PARTICIPATION

We welcome inquiries from students and researchers interested in
joining the project, as well as from companies interested in
collaboration or data partnerships. Please feel free to contact us using the forms below.