相关论文: Refined Detection for Gumbel Watermarking

In this paper, we introduce \emph{Luminark}, a training-free and probabilistically-certified watermarking method for general vision generative models. Our approach is built upon a novel watermark definition that leverages patch-level…

Weak signal identification and inference are very important in the area of penalized model selection, yet they are under-developed and not well-studied. Existing inference procedures for penalized estimators are mainly focused on strong…

Potential harms of Large Language Models such as mass misinformation and plagiarism can be partially mitigated if there exists a reliable way to detect machine generated text. In this paper, we propose a new watermarking method to detect…

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection…

The embedder and the detector (or decoder) are the two most important components of the digital watermarking systems. Thus in this work, we discuss how to design a better embedder and detector (or decoder). I first give a summary of the…

Generating samples given a specific label requires estimating conditional distributions. We derive a tractable upper bound of the Wasserstein distance between conditional distributions to lay the theoretical groundwork to learn conditional…

This paper addresses the design of an active cyberattack detection architecture based on multiplicative watermarking, allowing for detection of covert attacks. We propose an optimal design problem, relying on the so-called output-to-output…

Watermarking has emerged as a promising solution to counter harmful or deceptive AI-generated content by embedding hidden identifiers that trace content origins. However, the robustness of current watermarking techniques is still largely…

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

Water is the lifeblood of river networks, and its quality plays a crucial role in sustaining both aquatic ecosystems and human societies. Real-time monitoring of water quality is increasingly reliant on in-situ sensor technology. Anomaly…

Neural networks have increasingly influenced people's lives. Ensuring the faithful deployment of neural networks as designed by their model owners is crucial, as they may be susceptible to various malicious or unintentional modifications,…

Deep neural networks are vulnerable to malicious fine-tuning attacks such as data poisoning and backdoor attacks. Therefore, in recent research, it is proposed how to detect malicious fine-tuning of neural network models. However, it…

We propose a probabilistic formulation that enables sequential detection of multiple change points in a network setting. We present a class of sequential detection rules for certain functionals of change points (minimum among a subset), and…

This paper presents AutoMarks, an automated and transferable watermarking framework that leverages graph neural networks to reduce the watermark search overheads during the placement stage. AutoMarks's novel automated watermark search is…

This paper presents a despeckling method for Sentinel-1 GRD images based on the recently proposed framework "SAR2SAR": a self-supervised training strategy. Training the deep neural network on collections of Sentinel 1 GRD images leads to a…

Digital watermarks have been considered a promising way to fight software piracy. Graph-based watermarking schemes encode authorship/ownership data as control-flow graph of dummy code. In 2012, Chroni and Nikolopoulos developed an ingenious…

As Generative AI continues to become more accessible, the case for robust detection of generated images in order to combat misinformation is stronger than ever. Invisible watermarking methods act as identifiers of generated content,…

Watermarking is a technique that involves embedding nearly unnoticeable statistical signals within generated content to help trace its source. This work focuses on a scenario where an untrusted third-party user sends prompts to a trusted…

Major advancements have been made in the field of object detection and segmentation recently. However, when it comes to rare categories, the state-of-the-art methods fail to detect them, resulting in a significant performance gap between…

As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization…