VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
Double-i watermark: Protect- ing model copyright for llm fine-tuning.arXiv preprint arXiv:2402.14883
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
R-CoT embeds watermarks into LLM reasoning paths via redundant CoT and GRPO-based dual optimization, maintaining over 95% true positive rate under fine-tuning and post-training changes.
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
SIF creates semantically in-distribution fingerprints for LVLMs by distilling text watermarks into visual inputs and optimizing for robustness against detection and modification.
citing papers explorer
-
VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
-
R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models
R-CoT embeds watermarks into LLM reasoning paths via redundant CoT and GRPO-based dual optimization, maintaining over 95% true positive rate under fine-tuning and post-training changes.
-
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
-
SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models
SIF creates semantically in-distribution fingerprints for LVLMs by distilling text watermarks into visual inputs and optimizing for robustness against detection and modification.