Search papers, labs, and topics across Lattice.
3
0
5
2
Several open research questions are identified, including how to efficiently record incidents and how to determine whether vulnerabilities and incidents generalize, and privacy requirements are summarized and research directions for the secure and trustworthy deployment of AI agents are outlined.
Even state-of-the-art AI agents are surprisingly vulnerable to incremental attacks that gradually lead them to perform unsafe actions in realistic workplace scenarios.
Navigating the EU's regulatory maze for AI agents requires a 12-step compliance architecture and a detailed map linking agent actions to specific laws, or risk non-compliance with the AI Act.
