Search papers, labs, and topics across Lattice.
7
0
9
3
Cloned outputs from LLMs can be detected with over 87% accuracy using behavioral signatures, revealing significant vulnerabilities in prompt security.
Targeted bit-flip attacks can cripple Vision-Language-Action models, reducing their success rates to zero with just a few flips in key layers.
Achieving 92.1% mIoU without training or original cameras, Seed2GS revolutionizes object extraction from 3D scenes.
Coding agents guess their way through underspecified instructions, leading to alarming action-boundary violations that challenge the notion of safe autonomy.
Static scanners fail against adaptive evasions, but a new behavior-centric auditor can detect 97% of malicious skills with minimal false positives.
LLM agents can actually get *better* at coding when you strip away the unnecessary fluff in their skills, achieving a "less-is-more" effect.
Existing defenses against indirect prompt injection in LLM agents are riddled with flaws, as demonstrated by three new adaptive attacks that easily bypass them.
