Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
PURA achieves over three times the message match rate of existing unbiased watermarking methods, all while preserving text quality and speed.
PromptGraph reveals that modeling contextual relationships between text spans can dramatically enhance privacy preservation in LLM inference without sacrificing utility.
Achieve near-perfect covert communication even when tokenizers disagree, by selectively patching up tokenization mismatches on the fly.
