Related papers: SemBind: Binding Diffusion Watermarks to Semantics…
Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine learning-based detectors that predict if text is synthetic,…
Watermarking for diffusion images has drawn considerable attention due to the widespread use of text-to-image diffusion models and the increasing need for their copyright protection. Recently, advanced watermarking techniques, such as Tree…
Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in Large Vision-Language Models (LVLMs). However, vision-agnostic watermarks may introduce visually irrelevant tokens and disrupt…
Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to certify the robustness of semantic segmentation models against…
This paper introduces EmMark,a novel watermarking framework for protecting the intellectual property (IP) of embedded large language models deployed on resource-constrained edge devices. To address the IP theft risks posed by malicious…
Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…
The rise of Large Language Models (LLMs) has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and…
Malicious Deepfakes have led to a sharp conflict over distinguishing between genuine and forged faces. Although many countermeasures have been developed to detect Deepfakes ex-post, undoubtedly, passive forensics has not considered any…
Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models. It is, therefore, necessary to analyze the origin of…
Arbitrary Style Transfer (AST) achieves the rendering of real natural images into the painting styles of arbitrary art style images, promoting art communication. However, misuse of unauthorized art style images for AST may infringe on…
Watermarking methods have always been effective means of protecting intellectual property, yet they face significant challenges. Although existing deep learning-based watermarking systems can hide watermarks in images with minimal impact on…
With the rapid advancement of image generation techniques, robust forgery detection has become increasingly imperative to ensure the trustworthiness of digital media. Recent research indicates that the learned semantic concepts of…
Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…
Nowadays, three-dimensional meshes have been extensively used in several applications such as, industrial, medical, computer-aided design (CAD) and entertainment due to the processing capability improvement of computers and the development…
Watermarking is an essential technique for embedding an identifier (i.e., watermark message) within digital images to assert ownership and monitor unauthorized alterations. In face recognition systems, watermarking plays a pivotal role in…
Deepfake detection remains highly challenging, particularly in cross-dataset scenarios and complex real-world settings. This challenge mainly arises because artifact patterns vary substantially across different forgery methods, whereas…
Ethical concerns surrounding copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models. One effective solution involves watermarking the generated images. However,…
We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor would be invariant to…
Watermarking LLM-generated text is critical for content attribution and misinformation prevention. However, existing methods compromise text quality, require white-box model access and logit manipulation. These limitations exclude API-based…
The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking…