What would you like to search for?
What would you like to search for?

Dr. Yisroel Mirsky awarded prestigious ERC grant to safeguard future AI systems

Dr. Yisroel Mirsky has been awarded a European Research Council (ERC) Starting Grant to investigate how to safeguard future artificial general intelligence systems.

Dr. Yisroel Mirsky | Photo: Dani Machlis/BGU

"This project explores how to make future Artificial General Intelligence (AGI) systems safe and trustworthy. Unlike today’s AI, which can perform narrow tasks like generating text or recognizing images, AGI would have human-level abilities to learn, reason, and adapt across many different domains. The research anticipates the risks posed by such powerful systems and develops ways to ensure they benefit society without causing unintended harm," explains Dr. Mirsky.

Dr. Mirsky is a tenured Assistant Professor and Zuckerman Faculty Scholar in the Department of Software and Information Systems Engineering at Ben-Gurion University. He is the head of the Offensive AI Research Lab at CBG. He received his PhD from BGU in 2018 and was a postdoctoral fellow for two years at the Georgia Institute of Technology in the research labs of Prof. Wenke Lee.

His main research interests include AI Safety, Agent Security, Deepfakes, and Adversarial Machine Learning. Dr. Mirsky has published his work in some of the best security venues: USENIX, CCS, NDSS, Euro S&P, Black Hat, DEF CON, RSA, CSF, AISec, etc.

The ERC Starting Grant is one of the most prestigious competitive research grants in the world. Providing 1.5 million euros over five years, it is designed to support promising young researchers studying current and future challenges.

Dr. Yisroel Mirsky has been awarded a European Research Council (ERC) Starting Grant to investigate how to safeguard future artificial general intelligence systems. Dr. Yisroel Mirsky | Photo: Dani Machlis/BGU "This project explores how to make future Artificial General Intelligence (AGI) systems safe and trustworthy. Unlike today’s AI, which can perform narrow tasks like generating text or recognizing images, AGI would have human-level abilities to learn, reason, and adapt across many different domains. The research anticipates the risks posed by such powerful systems and develops ways to ensure they benefit society without causing unintended harm," explains Dr. Mirsky. Dr. Mirsky is a tenured Assistant Professor and Zuckerman Faculty Scholar in the Department of Software and Information Systems Engineering at Ben-Gurion University. He is the head of the Offensive AI Research Lab at CBG. He received his PhD from BGU in 2018 and was a postdoctoral fellow for two years at the Georgia Institute of Technology
237