DualGuard uses adaptive dual-stream watermark signals to detect and trace both paraphrase and spoofing attacks in LLM outputs while preserving text quality.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Passages made from high-convergence sentences improve LLM performance on inferential questions compared to cosine similarity selection.
citing papers explorer
-
DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
DualGuard uses adaptive dual-stream watermark signals to detect and trace both paraphrase and spoofing attacks in LLM outputs while preserving text quality.
-
Context Convergence Improves Answering Inferential Questions
Passages made from high-convergence sentences improve LLM performance on inferential questions compared to cosine similarity selection.