Related papers: AMUSE: Adaptive Multi-Segment Encoding for Dataset…

We present a novel technique for modulating the appearance frequency of a few tokens within a dataset for encoding an invisible watermark that can be used to protect ownership rights upon data. We develop optimal as well as fast heuristic…

Watermarking is a technique which consists in introducing a brand, the name or the logo of the author, in an image in order to protect it against illegal copy. The capacity of the existing watermark channel is often limited. We propose in…

The Segment Anything Model (SAM) has revolutionized natural image segmentation, nevertheless, its performance on underwater images is still restricted. This work presents AquaSAM, the first attempt to extend the success of SAM on underwater…

In recent years as the internet age continues to grow, sharing images on social media has become a common occurrence. In certain cases, watermarks are used as protection for the ownership of the image, however, in more cases, one may wish…

Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However,…

Segment anything model (SAM) has shown impressive general-purpose segmentation performance on natural images, but its performance on camouflaged object detection (COD) is unsatisfactory. In this paper, we propose SAM-COD that performs…

Content-independent watermarks and block-wise independency can be considered as vulnerabilities in semi-fragile watermarking methods. In this paper to achieve the objectives of semi-fragile watermarking techniques, a method is proposed to…

This paper presents a novel framework for importance-aware adaptive data transmission, designed specifically for real-time computer vision (CV) applications where task-specific fidelity is critical. An importance-weighted mean square error…

Modern generative diffusion models rely on vast training datasets, often including images with uncertain ownership or usage rights. Radioactive watermarks -- marks that transfer to a model's outputs -- can help detect when such unauthorized…

Image Compression plays a very important role in image processing especially when we are to send the image on the internet. The threat to the information on the internet increases and image is no exception. Generally the image is sent on…

Deep watermarking methods often share similar encoder-decoder architectures, yet differ substantially in their functional behaviors. We propose DiM, a new multi-dimensional watermarking framework that formulates watermarking as a…

As recent text-conditioned diffusion models have enabled the generation of high-quality images, concerns over their potential misuse have also grown. This issue is critical in the medical domain, where text-conditioned generated medical…

Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the…

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…

As digital content can be copied easily, Copyright infringement has become a concern nowadays. Providing a solution to prevent the abuse of such contents is very necessary. One of the most common methods to solve this problem is…

Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its reliability has been…

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific object categories. To address this limitation, we propose…

State-of-the-art text-to-image models generate photorealistic images at an unprecedented speed. This work focuses on models that operate in a bitwise autoregressive manner over a discrete set of tokens that is practically infinite in size.…

Generative models that can produce realistic images have improved significantly in recent years. The quality of the generated content has increased drastically, so sometimes it is very difficult to distinguish between the real images and…