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

• Published in: IEEE access Vol. 12; p. 1
• Main Authors: Munyer, Travis, Tanvir, Abdullah, Das, Arjon, Zhong, Xin
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Blindness; Classifiers; Deep learning; Detection algorithms; Large Language Model Text Detection; Large language models; Machine learning; Proposals; Reliability; Robustness; Semantics; Text processing; Text Source Detection; Text Watermarking; Transformers; Watermarking
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3376693

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.