Related papers: SAiW: Source-Attributable Invisible Watermarking f…
The proliferation of AI-generated content brings significant concerns on the forensic and security issues such as source tracing, copyright protection, etc, highlighting the need for effective watermarking technologies. Font-based text…
With generative models producing high quality images that are indistinguishable from real ones, there is growing concern regarding the malicious usage of AI-generated images. Imperceptible image watermarking is one viable solution towards…
To ensure the responsible distribution and use of open-source deep neural networks (DNNs), DNN watermarking has become a crucial technique to trace and verify unauthorized model replication or misuse. In practice, black-box watermarks…
Backdoor watermarking has emerged as the predominant approach for protecting public datasets, enabling dataset ownership verification (DOV) through embedded triggers that induce predefined model behaviors. While existing works assume that…
Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…
The growing use of large language models (LLMs) for sensitive applications has highlighted the need for effective watermarking techniques to ensure the provenance and accountability of AI-generated text. However, most existing watermarking…
As machine- and AI-generated content proliferates, protecting the intellectual property of generative models has become imperative, yet verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of…
Recently, diffusion models (DMs) have become the state-of-the-art method for image synthesis. Editing models based on DMs, known for their high fidelity and precision, have inadvertently introduced new challenges related to image copyright…
Robust reversible watermarking (RRW) enables copyright protection for images while overcoming the limitation of distortion introduced by watermark itself. Current RRW schemes typically employ a two-stage framework, which fails to achieve…
Current passive deepfake face-swapping detection methods encounter significance bottlenecks in model generalization capabilities. Meanwhile, proactive detection methods often use fixed watermarks which lack a close relationship with the…
The widespread use of AI-generated content from diffusion models has raised significant concerns regarding misinformation and copyright infringement. Watermarking is a crucial technique for identifying these AI-generated images and…
Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and security risks. Dataset watermarking has been proposed to ensure…
The rapid advancement of voice generation technologies has enabled the synthesis of speech that is perceptually indistinguishable from genuine human voices. While these innovations facilitate beneficial applications such as personalized…
Proactive Deepfake detection via robust watermarks has seen interest ever since passive Deepfake detectors encountered challenges in identifying high-quality synthetic images. However, while demonstrating reasonable detection performance,…
Training deep neural networks from scratch could be computationally expensive and requires a lot of training data. Recent work has explored different watermarking techniques to protect the pre-trained deep neural networks from potential…
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…
Language models now routinely produce text that is difficult to distinguish from human writing, raising the need for robust tools to verify content provenance. Watermarking has emerged as a promising countermeasure, with existing work…
The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing and novel semantic editing attacks. Current deep…
Identifying the origin of data is crucial for data provenance, with applications including data ownership protection, media forensics, and detecting AI-generated content. A standard approach involves embedding-based retrieval techniques…
As image generation models grow increasingly powerful and accessible, concerns around authenticity, ownership, and misuse of synthetic media have become critical. The ability to generate lifelike images indistinguishable from real ones…