mlsanityData to 14 Oct 2026

DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text

arXiv 2305.05773 ↗First posted 9 May 2023cs.MM cs.LGcited by 23

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

Abstract (arXiv)

The rapid advancement of Large Language Models (LLMs) has significantly enhanced the capabilities of text generators. With the potential for misuse escalating, the importance of discerning whether texts are human-authored or generated by LLMs has become paramount. Several preceding studies have ventured to address this challenge by employing binary classifiers to differentiate between human-written and LLM-generated text. Nevertheless, the reliability of these classifiers has been subject to question. Given that consequential decisions may hinge on the outcome of such classification, it is imperative that text source detection is of high caliber. In light of this, the present paper introduces DeepTextMark, a deep learning-driven text watermarking methodology devised for text source identification. By leveraging Word2Vec and Sentence Encoding for watermark insertion, alongside a transformer-based classifier for watermark detection, DeepTextMark epitomizes a blend of blindness, robustness, imperceptibility, and reliability. As elaborated within the paper, these attributes are crucial for universal text source detection, with a particular emphasis in this paper on text produced by LLMs. DeepTextMark offers a viable "add-on" solution to prevailing text generation frameworks, requiring no direct access or alterations to the underlying text generation mechanism. Experimental evaluations underscore the high imperceptibility, elevated detection accuracy, augmented robustness, reliability, and swift execution of DeepTextMark.

Key facts. Cited by 23 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 7 of its 24 references that are in the map. First posted on arXiv 9 May 2023.

Builds on

7 of 24 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Can AI-Generated Text be Reliably Detected?17 Mar
  2. 2023A Watermark for Large Language Models24 Jan

Other references · 5

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  5. 2018Universal Sentence Encodercited by 489

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 9; 2026: 5.

23 papers.

Sort:

By area:

  1. 2023Publicly-Detectable Watermarking for Language Modelscited by 76
  2. 2024Provably Robust Multi-bit Watermarking for AI-generated Textcited by 47
  3. 2024PostMark: A Robust Blackbox Watermark for Large Language Modelscited by 29
  4. 2024Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approachcited by 22
  5. 2025CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Qualitycited by 19
  6. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  7. 2024Robust Multi-bit Text Watermark with LLM-based Paraphraserscited by 10
  8. 2024Watermarking Language Models through Language Modelscited by 8
  9. 2024PersonaMark: Personalized LLM watermarking for model protection and user attributioncited by 7
  10. 2025RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Modelscited by 6
  11. 2025Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarkingcited by 6
  12. 2025WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarkingcited by 6
11 more
  1. 2024On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attackscited by 4
  2. 2024CredID: Credible Multi-Bit Watermark for Large Language Models Identificationcited by 4
  3. 2025Majority Bit-Aware Watermarking For Large Language Modelscited by 4
  4. 2025EditMark: Watermarking Large Language Models based on Model Editingcited by 4
  5. 2026XMark: Reliable Multi-Bit Watermarking for LLM-Generated Textscited by 3
  6. 2025Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimizationcited by 1
  7. 2026Geometric Reciprocity: Unlocking Self-Supervision for Stereoscopic Video Generationcited by 1
  8. 2025PRIVMARK: Private Large Language Models Watermarking with MPCcited by 0
  9. 2026Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraintscited by 0
  10. 2026Can Watermarking Techniques Help Prevent LLM Model Stealing?cited by 0
  11. 2026Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Textcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Necessary and Sufficient Watermark for Large Language Models
  2. 2024A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules
  3. 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
  4. 2023From Text to Source: Results in Detecting Large Language Model-Generated Content
  5. 2025PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
  6. 2023Three Bricks to Consolidate Watermarks for Large Language Models
  7. 2025DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language Models
  8. 2025BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks