mlsanityData to 7 Oct 2026

Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models

arXiv 2402.14007 ↗First posted 21 Feb 2024cs.CL cs.AIcited by 27

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Text watermarking technology aims to tag and identify content produced by large language models (LLMs) to prevent misuse. In this study, we introduce the concept of cross-lingual consistency in text watermarking, which assesses the ability of text watermarks to maintain their effectiveness after being translated into other languages. Preliminary empirical results from two LLMs and three watermarking methods reveal that current text watermarking technologies lack consistency when texts are translated into various languages. Based on this observation, we propose a Cross-lingual Watermark Removal Attack (CWRA) to bypass watermarking by first obtaining a response from an LLM in a pivot language, which is then translated into the target language. CWRA can effectively remove watermarks, decreasing the AUCs to a random-guessing level without performance loss. Furthermore, we analyze two key factors that contribute to the cross-lingual consistency in text watermarking and propose X-SIR as a defense method against CWRA. Code: https://github.com/zwhe99/X-SIR.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 16 of its 35 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

16 of 35 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023A Survey of Text Watermarking in the Era of Large Language Models13 Dec
  2. 2023Provable Robust Watermarking for AI-Generated Text30 Jun
  3. 2023Watermarking Text Generated by Black-Box Language Models14 May

Other references · 13

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  6. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  7. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  8. 2019ELI5: Long Form Question Answeringcited by 567
  9. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  10. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  11. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  12. 2024Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Modelcited by 33
1 more
  1. 2023Composition-contrastive Learning for Sentence Embeddingscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 7; 2026: 13.

27 papers.

Sort:

By area:

  1. 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-offcited by 48
  2. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  3. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarkingcited by 14
  4. 2024Watermarking Language Models with Error Correcting Codescited by 10
  5. 2024Can Watermarked LLMs be Identified by Users via Crafted Prompts?cited by 10
  6. 2025Character-Level Perturbations Disrupt LLM Watermarkscited by 7
  7. 2024Survey on Plagiarism Detection in Large Language Models: The Impact of ChatGPT and Gemini on Academic Integritycited by 5
  8. 2024On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attackscited by 4
  9. 2025Robustness Assessment and Enhancement of Text Watermarking for Google's SynthIDcited by 4
  10. 2026PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attackscited by 4
  11. 2026A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Modelcited by 3
  12. 2026Sequential Behavioral Watermarking for LLM Agentscited by 3
15 more
  1. 2025SoK: Are Watermarks in LLMs Ready for Deployment?cited by 2
  2. 2026Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarkingcited by 2
  3. 2025Cross-Lingual Summarization as a Black-Box Watermark Removal Attackcited by 1
  4. 2026AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Modelscited by 1
  5. 2026WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiencycited by 1
  6. 2026Auditing Cross-Lingual Fairness in Language Model Watermarkingcited by 1
  7. 2024Watermark Smoothing Attacks against Language Modelscited by 0
  8. 2025Toward Copyright Integrity and Verifiability via Multi-Bit Watermarking for Intelligent Transportation Systemscited by 0
  9. 2025Signature vs. Substance: Evaluating the Balance of Adversarial Resistance and Linguistic Quality in Watermarking Large Language Modelscited by 0
  10. 2026Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Modelscited by 0
  11. 2026Signature filtering: a lightweight enhancement for statistical watermark detection in large language modelscited by 0
  12. 2026Robust Text Watermarking for Large Language Models via Dual Semantic Embeddingscited by 0
  13. 2026Making Open-Source Text LLM Watermarks Durable Against Mergingcited by 0
  14. 2026Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Textcited by 0
  15. 2026Watermarks Without Verification: AI Text Watermarking After the EU AI Actcited by 0