Related papers: WaterVIB: Learning Minimal Sufficient Watermark Re…
The availability of bandwidth for internet access is sufficient enough to communicate digital assets. These digital assets are subjected to various types of threats. [19] As a result of this, protection mechanism required for the protection…
Deep learning-based image watermarking, while robust against conventional distortions, remains vulnerable to advanced adversarial and regeneration attacks. Conventional countermeasures, which jointly optimize the encoder and decoder via a…
Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…
To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark. The capacity of the watermark quantify the maximal volume of information that can be verified from the watermarked…
Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability. To improve the interpretability of vision-language models such as CLIP, we…
Digital watermarking techniques are crucial for copyright protection and source identification of images, especially in the era of generative AI models. However, many existing watermarking methods, particularly content-agnostic approaches…
Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…
There has been a remarkable increase in the data exchange over web and the widespread use of digital media. As a result, multimedia data transfers also had a boost up. The mounting interest with reference to digital watermarking throughout…
Instruction-driven image editing allows users to quickly edit an image according to text instructions in a forward pass. Nevertheless, malicious users can easily exploit this technique to create fake images, which could cause a crisis of…
Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential. To evaluate and improve the effectiveness of watermark, watermark removal attracts…
With the success of autoregressive learning in large language models, it has become a dominant approach for text-to-image generation, offering high efficiency and visual quality. However, invisible watermarking for visual autoregressive…
DNN-based watermarking methods are rapidly developing and delivering impressive performances. Recent advances achieve resolution-agnostic image watermarking by reducing the variant resolution watermarking problem to a fixed resolution…
In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a benchmark for assessing image watermark robustness, overcoming…
Verifying the authenticity of AI-generated text has become increasingly important with the rapid advancement of large language models, and unbiased watermarking has emerged as a promising approach due to its ability to preserve output…
Robust Reversible Watermarking (RRW) enables perfect recovery of cover images and watermarks in lossless channels while ensuring robust watermark extraction in lossy channels. Existing RRW methods, mostly non-deep learning-based, face…
As there are increasing needs of sharing data for machine learning, there is growing attention for the owners of the data to claim the ownership. Visible watermarking has been an effective way to claim the ownership of visual data, yet the…
Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. In this paper, we introduce a novel technique called Tree-Ring Watermarking that robustly…
AIGC (AI-Generated Content) has achieved tremendous success in many applications such as text-to-image tasks, where the model can generate high-quality images with diverse prompts, namely, different descriptions in natural languages. More…
We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries.…
A wide range of Deep Natural Language Processing (NLP) models integrates continuous and low dimensional representations of words and documents. Surprisingly, very few models study representation learning for authors. These representations…