Search papers, labs, and topics across Lattice.
3
0
4
0
LLMs can be jailbroken with 90% success by subtly "salami slicing" harmful intent across multiple turns, even against state-of-the-art models like GPT-4o and Gemini.
A single malicious message can trigger a self-replicating worm, ClawWorm, that autonomously infects and propagates across entire LLM agent ecosystems, even surviving agent restarts.
Over half of LLM agent tool interactions leak sensitive data, and AgentRaft can catch them with high accuracy.
