Search papers, labs, and topics across Lattice.
3
0
5
9
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.
Exploiting a vulnerability in LLM APIs allows attackers to extract proprietary reasoning and sensitive data without directly breaching the more capable models.
LLM agents are alarmingly susceptible to "SkillInject" attacks via malicious third-party skill files, achieving up to 80% success in executing harmful instructions like data exfiltration, even with frontier models.
