Search papers, labs, and topics across Lattice.
3
0
6
3
HazardAuditor is introduced, an execution-grounded framework that runs heterogeneous agents in controlled environments and normalizes their interactions into a canonical event representation for cross-framework supervision, and observes that token-level post-training objectives create a structural mismatch for generative guards, causing longer rationales to dominate gradient updates.
User invocation choices can amplify coding agent vulnerability, with task type causing a staggering 4.5-fold difference in attack 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.
