DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text
May 09, 2023 ยท Declared Dead ยท ๐ IEEE Access
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Travis Munyer, Abdullah Tanvir, Arjon Das, Xin Zhong
arXiv ID
2305.05773
Category
cs.MM: Multimedia
Cross-listed
cs.LG
Citations
37
Venue
IEEE Access
Last Checked
2 months ago
Abstract
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.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Multimedia
R.I.P.
๐ป
Ghosted
๐
๐
Old Age
Quality Assessment of In-the-Wild Videos
R.I.P.
๐ป
Ghosted
Viewport-Adaptive Navigable 360-Degree Video Delivery
R.I.P.
๐ป
Ghosted
A Comprehensive Survey on Cross-modal Retrieval
R.I.P.
๐ป
Ghosted
An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges
R.I.P.
๐ป
Ghosted
A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted