Search papers, labs, and topics across Lattice.
2
0
4
5
LLMs can misinterpret benign text as physically dangerous actions, but a new probing method achieves over 99% accuracy in identifying these risks without relying on explicit unsafe keywords.
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.
