Search papers, labs, and topics across Lattice.
Chiao Tung University ♣, IBM Research ♠ Hon Hai Research Institute
4
0
5
TRACE reveals how token influence can expose malicious manipulations in RAG systems, achieving high detection rates without heavy computational costs.
RAS reveals that internal representation alignment can serve as a reliable and efficient metric for LLM safety, outperforming conventional output-based evaluations.
CodeSentinel outperforms existing defenses by achieving an impressive 0.80 F1 score in detecting indirect prompt injections in code contexts.
Uncovering how VR motion sensors can reconstruct brainwave data reveals a startling new vector for privacy breaches in the Metaverse.
