Related papers: Watermark-based Detection and Attribution of AI-Generated Content

Watermark-based Detection and Attribution of AI-Generated Content

URL: http://arxiv.org/abs/2404.04254v1
Date: Fri, 5 Apr 2024 17:58:52 GMT
Title: Watermark-based Detection and Attribution of AI-Generated Content
Authors: Zhengyuan Jiang, Moyang Guo, Yuepeng Hu, Neil Zhenqiang Gong,
Abstract summary: We provide the first systematic study on user-aware detection and attribution of AI-generated content. Specifically, we theoretically study the detection and attribution performance via rigorous probabilistic analysis. We develop an efficient algorithm to select watermarks for the users to enhance attribution performance.
Score: 34.913290430783185
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Several companies--such as Google, Microsoft, and OpenAI--have deployed techniques to watermark AI-generated content to enable proactive detection. However, existing literature mainly focuses on user-agnostic detection. Attribution aims to further trace back the user of a generative-AI service who generated a given content detected as AI-generated. Despite its growing importance, attribution is largely unexplored. In this work, we aim to bridge this gap by providing the first systematic study on watermark-based, user-aware detection and attribution of AI-generated content. Specifically, we theoretically study the detection and attribution performance via rigorous probabilistic analysis. Moreover, we develop an efficient algorithm to select watermarks for the users to enhance attribution performance. Both our theoretical and empirical results show that watermark-based detection and attribution inherit the accuracy and (non-)robustness properties of the watermarking method.

Related papers

IConMark: Robust Interpretable Concept-Based Watermark For AI Images [50.045011844765185]
We propose IConMark, a novel in-generation robust semantic watermarking method.<n>IConMark embeds interpretable concepts into AI-generated images, making it resilient to adversarial manipulation.<n>We demonstrate its superiority in terms of detection accuracy and maintaining image quality.
arXiv Detail & Related papers (2025-07-17T05:38:30Z)
WMCopier: Forging Invisible Image Watermarks on Arbitrary Images [21.17890218813236]
We propose WMCopier, an effective watermark forgery attack that operates without requiring prior knowledge of or access to the target watermarking algorithm.<n>Our approach first models the target watermark distribution using an unconditional diffusion model, and then seamlessly embeds the target watermark into a non-watermarked image.<n> Experimental results demonstrate that WMCopier effectively deceives both open-source and closed-source watermark systems.
arXiv Detail & Related papers (2025-03-28T11:11:19Z)
ESpeW: Robust Copyright Protection for LLM-based EaaS via Embedding-Specific Watermark [50.08021440235581]
Embeds as a Service (Eding) is emerging as a crucial role in AI applications. Eding is vulnerable to model extraction attacks, highlighting the urgent need for copyright protection. We propose a novel embedding-specific watermarking (ESpeW) mechanism to offer robust copyright protection for Eding.
arXiv Detail & Related papers (2024-10-23T04:34:49Z)
Certifiably Robust Image Watermark [57.546016845801134]
Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns. We propose the first image watermarks with certified robustness guarantees against removal and forgery attacks.
arXiv Detail & Related papers (2024-07-04T17:56:04Z)
Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious? [21.06493827123594]
steganalysis attacks can extract and remove the watermark with minimal perceptual distortion. We show how averaging a collection of watermarked images could reveal the underlying watermark pattern. We propose security guidelines calling for using content-adaptive watermarking strategies and performing security evaluation against steganalysis.
arXiv Detail & Related papers (2024-06-13T12:01:28Z)
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees [33.61946642460661]
This paper introduces a robust and agile watermark detection framework, dubbed as RAW. We employ a classifier that is jointly trained with the watermark to detect the presence of the watermark. We show that the framework provides provable guarantees regarding the false positive rate for misclassifying a watermarked image.
arXiv Detail & Related papers (2024-01-23T22:00:49Z)
A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models [65.40460716619772]
Our research focuses on the importance of a textbfDistribution-textbfPreserving (DiP) watermark. Contrary to the current strategies, our proposed DiPmark simultaneously preserves the original token distribution during watermarking. It is detectable without access to the language model API and prompts (accessible), and is provably robust to moderate changes of tokens.
arXiv Detail & Related papers (2023-10-11T17:57:35Z)
Unbiased Watermark for Large Language Models [67.43415395591221]
This study examines how significantly watermarks impact the quality of model-generated outputs. It is possible to integrate watermarks without affecting the output probability distribution. The presence of watermarks does not compromise the performance of the model in downstream tasks.
arXiv Detail & Related papers (2023-09-22T12:46:38Z)
Evading Watermark based Detection of AI-Generated Content [45.47476727209842]
A generative AI model can generate extremely realistic-looking content. Watermark has been leveraged to detect AI-generated content. A content is detected as AI-generated if a similar watermark can be decoded from it.
arXiv Detail & Related papers (2023-05-05T19:20:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.