Search papers, labs, and topics across Lattice.
4
0
5
2
Skill compositions can exploit safety gaps, with CompoSkill achieving up to 83.3% success in forming risky chains from individually certified skills.
Trajectory-poisoning can turn untrusted experiences into trusted skills, embedding malicious behaviors into self-evolving agents with alarming success rates.
Malicious audio instructions can stealthily hijack multimodal agents, achieving a 69.10% success rate in real-world scenarios.
Vera reveals that existing LLM agents exhibit up to 93.9% vulnerability to multi-channel attacks, highlighting a significant gap in current safety evaluations.
