相关论文: SHIFT: Stochastic Hidden-Trajectory Deflection for…

Diffusion models have established new state of the art in a multitude of computer vision tasks, including image restoration. Diffusion-based inverse problem solvers generate reconstructions of exceptional visual quality from heavily…

In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has become a vital tool to address these challenges, safeguarding…

This paper proposes a novel approach towards image authentication and tampering detection by using watermarking as a communication channel for semantic information. We modify the HiDDeN deep-learning watermarking architecture to embed and…

Watermarking approaches are widely used to identify if images being circulated are authentic or AI-generated. Determining the robustness of image watermarking methods in the ``no-box'' setting, where the attacker is assumed to have no…

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…

Diffusion models excel at generating high-quality, diverse images but suffer from training data memorization, raising critical privacy and safety concerns. Data unlearning has emerged to mitigate this issue by removing the influence of…

Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice…

Robot failure is detrimental and disruptive, often requiring human intervention to recover. Our vision is 'fail-active' operation, allowing robots to safely complete their tasks even when damaged. Focusing on 'actuation failures', we…

Watermark has been widely deployed by industry to detect AI-generated images. The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature. However, the…

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. Existing methods…

Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adversarial patch…

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…

Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained…

Discrete diffusion language models have shown strong potential for text generation, yet standard supervised fine-tuning (SFT) misaligns with their semi-autoregressive inference: training randomly masks tokens across the entire response,…

Watermarking is an important mechanism for provenance and copyright protection of diffusion-generated images. Training-free methods, exemplified by Gaussian Shading, embed watermarks into the initial noise of diffusion models with…

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…

In contemporary deep learning, a prevalent and effective workflow for solving low-data problems is adapting powerful pre-trained foundation models (FMs) to new tasks via parameter-efficient fine-tuning (PEFT). However, while empirically…

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…

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.…