Search papers, labs, and topics across Lattice.
5
0
7
12
A single manipulated search result can dramatically amplify the effectiveness of attacks on LLM-based search agents, revealing critical vulnerabilities in their evidence-gathering processes.
Multi-turn jailbreaks exploit user intent in ways that traditional safety measures fail to detect, revealing a critical vulnerability in LLM interactions.
Environmental illusions can degrade lane detection accuracy by over 7%, posing serious safety risks for autonomous vehicles.
CUTh-Solver achieves unprecedented speedups in thermal simulations, outperforming existing GPU solvers by over 25 times.
Even if adversaries try to scrub the watermark, Cert-LAS offers provable guarantees for verifying ownership of text-to-image diffusion models.
