Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
A single adversarial auditor can't fool Auditopus, a decentralized LLM fairness auditing system that achieves up to 78% error reduction against fairwashing attacks.
Privacy-preserving vector search schemes reveal a surprising trade-off landscape, with some methods matching plaintext performance while others impose hefty costs on usability.
RankGuard outperforms traditional centralized OLTR systems by ensuring robust defenses against poisoning attacks while enhancing efficiency in decentralized environments.
LLM agents can now detect configuration drift in cloud infrastructure more reliably, even when their tools return garbage.