Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
User invocation choices can amplify coding agent vulnerability, with task type causing a staggering 4.5-fold difference in attack success rates.
AEGIS can effectively defend against Indirect Prompt Injection attacks while maintaining low latency and high utility, a breakthrough for LLM safety.
Adversaries can exploit multimodal guardrails to misclassify safe inputs as unsafe, achieving an alarming 84% success rate in disrupting service availability.
