Search papers, labs, and topics across Lattice.
5
0
4
5
Trajectory-poisoning can turn untrusted experiences into trusted skills, embedding malicious behaviors into self-evolving agents with alarming success rates.
Vera reveals that existing LLM agents exhibit up to 93.9% vulnerability to multi-channel attacks, highlighting a significant gap in current safety evaluations.
Guard models trained with BraveGuard can detect safety threats in computer-use agents with over 82% accuracy, a significant leap from conventional methods.
LLM-powered autonomous agents are alarmingly susceptible to multi-turn, context-aware attacks that bypass standard security measures, nearly doubling the risk trigger rate.
Autonomous LLM agents are riddled with vulnerabilities, as point defenses fail to address cross-temporal and multi-stage systemic risks like memory poisoning and intent drift.
