Search papers, labs, and topics across Lattice.
5
0
8
6
Existing security scanners misidentify nearly half of MCP server risks, challenging the reliability of current security assessments in LLM applications.
AEGIS achieves near-zero attack success rates against visual synonym jailbreaks while preserving the fidelity of benign outputs, reshaping the defense landscape for text-to-image models.
SrDetection uncovers hidden data leakage patterns in Code LLMs, boosting detection accuracy by over 21 points without relying on fragile heuristics.
Reusing cached plans can cut computational costs by over 80% without sacrificing performance, but only if you adaptively manage prediction mismatches.
Current LLMs can autonomously penetrate systems with success rates up to 69.3%, revealing alarming implications for cybersecurity.
