Search papers, labs, and topics across Lattice.
6
1
7
3
Static scanners fail against adaptive evasions, but a new behavior-centric auditor can detect 97% of malicious skills with minimal false positives.
Coding agents guess their way through underspecified instructions, leading to alarming action-boundary violations that challenge the notion of safe autonomy.
AutoSpec achieves up to 4.8x higher F1 scores than traditional methods, transforming safety rule evolution into a precise, interpretable process for LLM agents.
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.
Turns out, "secure" weight release schemes like TaylorMLP aren't so secure after all, as this paper cracks them open with formal cryptographic attacks.
