Search papers, labs, and topics across Lattice.
CISPA Helmholtz Center for Information Security
2
0
4
Shared workspace files can turn stateful LLM assistants into self-replicating malware vectors, silently compromising up to 80% of independent agents across eight consecutive hops via persistent memory.
Forget expensive multilingual annotations: this framework lets you evaluate LLMs in new languages by transferring knowledge from English, with surprisingly strong results.
