相关论文: CLUE-MARK: Watermarking Diffusion Models using CLW…

With the explosive growth of internet technology, easy transfer of digital multimedia is feasible. However, this kind of convenience with which authorized users can access information, turns out to be a mixed blessing due to information…

Image generative models have become increasingly popular, but training them requires large datasets that are costly to collect and curate. To circumvent these costs, some parties may exploit existing models by using the generated images as…

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern…

Digital watermarking has shown its effectiveness in protecting multimedia content. However, existing watermarking is predominantly tailored for specific media types, rendering them less effective for the protection of content displayed on…

Safeguarding intellectual property and preventing potential misuse of AI-generated images are of paramount importance. This paper introduces a robust and agile plug-and-play watermark detection framework, dubbed as RAW. As a departure from…

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…

Invisible Image Watermarking is crucial for ensuring content provenance and accountability in generative AI. While Gen-AI providers are increasingly integrating invisible watermarking systems, the robustness of these schemes against forgery…

Text-to-Speech (TTS) diffusion models generate high-quality speech, which raises challenges for the model intellectual property protection and speech tracing for legal use. Audio watermarking is a promising solution. However, due to the…

The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…

We introduce the first watermark tailored for diffusion language models (DLMs), an emergent LLM paradigm able to generate tokens in arbitrary order, in contrast to standard autoregressive language models (ARLMs) which generate tokens…

We propose Easymark, a family of embarrassingly simple yet effective watermarks. Text watermarking is becoming increasingly important with the advent of Large Language Models (LLM). LLMs can generate texts that cannot be distinguished from…

The rapid advancement of generative AI has underscored the critical need for identifying image ownership and protecting copyrights. This makes post-processing image watermarking an essential tool -- it involves embedding a specific…

This paper presents a novel approach to deter unauthorized deepfakes and enable user tracking in generative models, even when the user has full access to the model parameters, by integrating key-based model authentication with watermarking…

Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe risks of unauthorized use. Although digital watermarking…

Watermarking (WM) is a critical mechanism for detecting and attributing AI-generated content. Current WM methods for Large Language Models (LLMs) are predominantly tailored for autoregressive (AR) models: They rely on tokens being generated…

Visible watermarks are widely-used in images to protect copyright ownership. Analyzing watermark removal helps to reinforce the anti-attack techniques in an adversarial way. Current removal methods normally leverage image-to-image…

We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer…

Deep neural networks (DNNs) have achieved significant success in real-world applications. However, safeguarding their intellectual property (IP) remains extremely challenging. Existing DNN watermarking for IP protection often require…

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 and has been widely deployed in industry. However,…