# Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning

arXiv: https://arxiv.org/abs/2504.06575 · HTML: https://mlsanity.com/paper/2504.06575/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 27 of 27)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Undetectable Watermarks for Language Models](https://mlsanity.com/paper/2306.09194/) (2023)
- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [A Semantic Invariant Robust Watermark for Large Language Models](https://mlsanity.com/paper/2310.06356/) (2023)
- [Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2310.10669/) (2023)
- [Robust Multi-bit Natural Language Watermarking through Invariant Features](https://mlsanity.com/paper/2305.01904/) (2023)
- [A Robust Semantics-based Watermark for Large Language Model against Paraphrasing](https://mlsanity.com/paper/2311.08721/) (2023)
- [REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models](https://mlsanity.com/paper/2310.12362/) (2023)
- [Watermarking Text Generated by Black-Box Language Models](https://mlsanity.com/paper/2305.08883/) (2023)
- [Adaptive Text Watermark for Large Language Models](https://mlsanity.com/paper/2401.13927/) (2024)
- [A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules](https://mlsanity.com/paper/2404.01245/) (2024)
- [k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text](https://mlsanity.com/paper/2402.11399/) (2024)
- [SoK: Watermarking for AI-Generated Content](https://mlsanity.com/paper/2411.18479/) (2024)
- [Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy](https://mlsanity.com/paper/2307.13808/) (2023)
- [No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices](https://mlsanity.com/paper/2402.16187/) (2024)
- [Tracing Text Provenance via Context-Aware Lexical Substitution](https://mlsanity.com/paper/2112.07873/) (2021)
- [Robust Detection of Watermarks for Large Language Models Under Human Edits](https://mlsanity.com/paper/2411.13868/) (2024)
- [Embarrassingly Simple Text Watermarks](https://mlsanity.com/paper/2310.08920/) (2023)
- [PostMark: A Robust Blackbox Watermark for Large Language Models](https://mlsanity.com/paper/2406.14517/) (2024)
- [Towards Optimal Statistical Watermarking](https://mlsanity.com/paper/2312.07930/) (2023)
- [Distributional Information Embedding: A Framework for Multi-bit Watermarking](https://mlsanity.com/paper/2501.16558/) (2025)

## Built on by (most cited first, 10 of 10)

- [PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints](https://mlsanity.com/paper/2509.21057/) (2025)
- [In-Context Watermarks for Large Language Models](https://mlsanity.com/paper/2505.16934/) (2025)
- [Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption](https://mlsanity.com/paper/2510.18333/) (2025)
- [Large Language Model Sourcing: A Survey](https://mlsanity.com/paper/2510.10161/) (2025)
- [Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking](https://mlsanity.com/paper/2510.01637/) (2025)
- [Scaling Participation in Modular AI Systems](https://mlsanity.com/paper/2606.07812/) (2026)
- [TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance](https://mlsanity.com/paper/2512.01314/) (2025)
- [Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks](https://mlsanity.com/paper/2608.12713/) (2026)
- [DenMark: Robust Semantic Watermarking for Diffusion Language Models](https://mlsanity.com/paper/2609.14257/) (2026)
- [Learning to Follow In-Context Watermark Instructions via Self-Distillation](https://mlsanity.com/paper/2608.29030/) (2026)

## Abstract (arXiv)

Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against removal attack. However, the security against spoofing attacks remains relatively understudied. For example, a piggyback attack can maliciously alter the meaning of watermarked text-transforming it into hate speech-while preserving the original watermark, thereby damaging the reputation of the LLM provider. We identify two core challenges that make defending against spoofing difficult: (1) the need for watermarks to be both sensitive to semantic-distorting changes and insensitive to semantic-preserving edits, and (2) the contradiction between the need to detect global semantic shifts and the local, auto-regressive nature of most watermarking schemes. To address these challenges, we propose a semantic-aware watermarking algorithm that post-hoc embeds watermarks into a given target text while preserving its original meaning. Our method introduces a semantic mapping model, which guides the generation of a green-red token list, contrastively trained to be sensitive to semantic-distorting changes and insensitive to semantic-preserving changes. Experiments on two standard benchmarks demonstrate strong robustness against removal attacks and security against spoofing attacks, including sentiment reversal and toxic content insertion, while maintaining high watermark detectability. Our approach offers a significant step toward more secure and semantically aware watermarking for LLMs. Our code is available at https://github.com/UCSB-NLP-Chang/contrastive-watermark.