RLSpoofer trains a 4B model on 100 watermarked paraphrase pairs to spoof PF watermarks at 62% success rate, far exceeding baselines trained on up to 10,000 samples.
De-mark: Watermark removal in large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
ISTS watermarking dynamically controls injection based on prompt semantics and uses two-sided detection to resist removal and forgery attacks in diffusion models.
GoCoMA fuses code stylometry and binary artifact images via hyperbolic Poincaré ball projection and geodesic-cosine attention to attribute LLM-generated code, outperforming baselines on CoDET-M4 and LLMAuthorBench.
citing papers explorer
-
RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
RLSpoofer trains a 4B model on 100 watermarked paraphrase pairs to spoof PF watermarks at 62% success rate, far exceeding baselines trained on up to 10,000 samples.
-
Towards Robust Content Watermarking Against Removal and Forgery Attacks
ISTS watermarking dynamically controls injection based on prompt semantics and uses two-sided detection to resist removal and forgery attacks in diffusion models.
-
GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution
GoCoMA fuses code stylometry and binary artifact images via hyperbolic Poincaré ball projection and geodesic-cosine attention to attribute LLM-generated code, outperforming baselines on CoDET-M4 and LLMAuthorBench.