Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
11
LLMs can be tricked into leaking sensitive data to attackers simply by being asked to fetch information from seemingly legitimate websites.
Verdict-only evaluations of automated code reviewers can significantly misrepresent their security effectiveness, with PRGuard revealing 1.38 times more target vulnerabilities than existing tools.
Achieve a 90% reduction in unsafe LLM generations with NeST, a parameter-efficient method that selectively tunes safety-relevant neurons, outperforming full fine-tuning and LoRA by orders of magnitude in parameter efficiency.
