An UP-TO-DATE collection list for Large Language Model (LLM) Watermark
-
- 2.1. Watermark stealing attack
- 2.2. Watermark removal attack
- 2.3. Watermark spoofing attack
- 2.4. Robust watermark
- A Watermark for Large Language Models
- ICML 2023
- http://arxiv.org/abs/2301.10226
- Publicly Detectable Watermarking for Language Models paper
- An Unforgeable Publicly Verifiable Watermark for Large Language Models
- On the Reliability of Watermarks for Large Language Models
- Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoring paper
- WatME: Towards Lossless Watermarking Through Lexical Redundancy
- ACL 2024
- https://aclanthology.org/2024.acl-long.496/
- Alias X-Mark: Towards Lossless Watermarking Through Lexical Redundancy paper
- Towards Optimal Statistical Watermarking paper
- Who Wrote this Code? Watermarking for Code Generation
- Natural language watermarking via paraphraser-based lexical substitution
- Artificial Intelligence
- https://linkinghub.elsevier.com/retrieve/pii/S000437022300005X
- Adaptive Text Watermark for Large Language Models
- ICML 2024
- paper
- Duwak: Dual Watermarks in Large Language Models
- ACL findings 2024
- https://aclanthology.org/2024.findings-acl.678
- Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
- NeurIPS workshop 2024
- https://arxiv.org/pdf/2402.05864
- WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
- SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
- NAACL 2024
- http://arxiv.org/abs/2310.03991
- k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
- ACL Findings 2024
- http://arxiv.org/abs/2402.11399
- A Semantic Invariant Robust Watermark for Large Language Models
- ICLR 2024
- http://arxiv.org/abs/2310.06356
- A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
- NAACL Findings 2024
- https://aclanthology.org/2024.findings-naacl.40
- Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models
- Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
- ICML 2024
- http://arxiv.org/abs/2402.18059
- SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text paper
- DeepTextMark: Deep Learning based Text Watermarking for Detection of Large Language Model Generated Text paper
- Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
- IEEE S&P 2021
- https://ieeexplore.ieee.org/document/9519400/
- PersonaMark: Personalized LLM watermarking for model protection and user attribution paper
- REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models
- USENIX Security 2024
- Provable Robust Watermarking for AI-Generated Text
- ICLR 2024
- http://arxiv.org/abs/2306.17439
- Watermarking LLMs with Weight Quantization paper
- EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models paper
- Watermarking Counterfactual Explanations paper
- Provably Robust Watermarks for Open-Source Language Models paper
- Learning to Watermark LLM-generated Text via Reinforcement Learning paper
- An Entropy-based Text Watermarking Detection Method
- WaterSeeker: Efficient Detection of Watermarked Segments in Large Documents paper
- Large Language Model Watermark Stealing With Mixed Integer Programming
- ACSAC 2024
- http://arxiv.org/abs/2405.19677
- Watermark Stealing in Large Language Models
- ICLR 2024 Workshop, ICML 2024
- http://arxiv.org/abs/2402.19361
- Bypassing LLM Watermarks with Color-Aware Substitutions
- Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
- NeurIPS 2023
- http://arxiv.org/abs/2303.13408
- Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
- ACL 2024
- http://arxiv.org/abs/2402.14007
- Watermark Smoothing Attacks against Language Models
- De-mark: Watermark Removal in Large Language Models
- No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
- NeurIPS 2024
- paper
- Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models
- ICML 2024
- paper
- offical cite
- WaterPark: A Robustness Assessment of Language Model Watermarking
-
$B^4$ : A Black-Box Scrubbing Attack on LLM Watermarks - Can AI-Generated Text be Reliably Detected? paper
- Lost in Overlap: Exploring Watermark Collision in LLMs paper
- Discovering Clues of Spoofed LM Watermarks
- On the Learnability of Watermarks for Language Models
- ICLR 2024
- http://arxiv.org/abs/2312.04469
- Edit Distance Robust Watermarks for Language Models
- NeurIPS 2024
- https://openreview.net/pdf?id=FZ45kf5pIA
- Waterfall: Framework for Robust and Scalable Text Watermarking paper
- Pseudorandom Error-Correcting Codes
- Can Watermarked LLMs be Identified by Users via Crafted Prompts?
- Three Bricks to Consolidate Watermarks for Large Language Models paper
- Provably Robust Multi-bit Watermarking for AI-generated Text via Error Correction Code paper
- Advancing Beyond Identification: Multi-bit Watermark for Large Language Models
- NAACL 2024
- https://aclanthology.org/2024.naacl-long.224
- Towards Codable Watermarking for Injecting Multi-bits Information to LLMs paper
- Robust Multi-bit Natural Language Watermarking through Invariant Features
- Multi-Bit Distortion-Free Watermarking for Large Language Models paper
- Towards Codable Watermarking for Injecting Multi-bits Information to LLMs
- Robust Multi-bit Text Watermark with LLM-based Paraphrasers paper
- PersonaMark: Personalized LLM watermarking for model protection and user attribution paper
- CODEIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code
- EMNLP findings 2024
- https://aclanthology.org/2024.findings-emnlp.541
- Enhancing Watermarked Language Models to Identify Users paper
- CredID: Credible Multi-Bit Watermark for Large Language Models Identification paper
- Unbiased Watermark for Large Language Models
- ICLR 2023
- http://arxiv.org/abs/2310.10669
- Undetectable Watermarks for Language Models
- Robust Distortion-free Watermarks for Language Models
- A Watermark for Low-entropy and Unbiased Generation in Large Language Models
- A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
- ICML 2024
- https://arxiv.org/abs/2310.07710
- Watermarking Language Models with Error Correcting Codes paper
- Scalable watermarking for identifying large language model outputs
- Multi-Bit Distortion-Free Watermarking for Large Language Models paper
- Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions paper
- Alias Pseudo- vs. True-Randomness: Rethinking Distortion-Free Watermarks of Language Models under Watermark Key Collisions paper
- Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
- ICML workshop
- https://openreview.net/pdf?id=79NfpNZkXW
- On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
- Optimizing Adaptive Attacks against Content Watermarks for Language Models
- Optimizing Watermarks for Large Language Models
- Performance Trade-offs of Watermarking Large Language Models paper
- Watermarking Makes Language Models Radioactive paper
- WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models paper
- Towards Better Statistical Understanding of Watermarking LLMs paper
- Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models paper
- A Survey of Text Watermarking in the Era of Large Language Models
- ACM Computing Surveys 2024
- http://arxiv.org/abs/2312.07913
- Mark My Words: Analyzing and Evaluating Language Model Watermarks paper
- WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models
- SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI paper
- SoK: Watermarking for AI-Generated Content paper