# Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs

arXiv: https://arxiv.org/abs/2403.10020 · HTML: https://mlsanity.com/paper/2403.10020/

## Key facts

- Cited by 4 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 12 of its 27 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## 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, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (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)
- [CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning](https://mlsanity.com/paper/2110.12925/) (2021)
- [GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick](https://mlsanity.com/paper/2402.12948/) (2024)
- [CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models](https://mlsanity.com/paper/2308.14401/) (2023)
- [Watermarking Text Data on Large Language Models for Dataset Copyright](https://mlsanity.com/paper/2305.13257/) (2023)

## Built on by (most cited first, 4 of 4)

- [WAPITI: A Watermark for Finetuned Open-Source LLMs](https://mlsanity.com/paper/2410.06467/) (2024)
- [Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation](https://mlsanity.com/paper/2510.18019/) (2025)
- [Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy](https://mlsanity.com/paper/2605.16796/) (2026)
- [The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs](https://mlsanity.com/paper/2610.03124/) (2026)

## Abstract (arXiv)

The proliferation of large language models (LLMs) in generating content raises concerns about text copyright. Watermarking methods, particularly logit-based approaches, embed imperceptible identifiers into text to address these challenges. However, the widespread usage of watermarking across diverse LLMs has led to an inevitable issue known as watermark collision during common tasks, such as paraphrasing or translation. In this paper, we introduce watermark collision as a novel and general philosophy for watermark attacks, aimed at enhancing attack performance on top of any other attacking methods. We also provide a comprehensive demonstration that watermark collision poses a threat to all logit-based watermark algorithms, impacting not only specific attack scenarios but also downstream applications.