Search papers, labs, and topics across Lattice.
This paper identifies critical challenges and future research directions concerning the security and privacy of agentic AI, synthesizing insights from a horizon-scanning exercise involving thirty experts across academia, industry, and government. The discussions highlighted emerging risks tied to the increasing autonomy of AI systems, emphasizing the need for robust frameworks to mitigate these threats. Key findings suggest that interdisciplinary collaboration is essential for developing effective strategies to address the complex security landscape of agentic AI.
Emerging risks from agentic AI demand urgent interdisciplinary collaboration to secure our future.
We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to engage in focused discussions and collaborative exercises on the emerging risks associated with the growing agency of AI.
