相关论文: A Crack in the Bark: Leveraging Public Knowledge t…
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 remarkable ability of diffusion models to generate high-fidelity images has led to their widespread adoption. However, concerns have also arisen regarding their potential to produce Not Safe for Work (NSFW) content and exhibit social…
Image generation algorithms are increasingly integral to diverse aspects of human society, driven by their practical applications. However, insufficient oversight in artificial Intelligence generated content (AIGC) can facilitate the spread…
Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's…
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…
Machine learning involves expensive data collection and training procedures. Model owners may be concerned that valuable intellectual property can be leaked if adversaries mount model extraction attacks. As it is difficult to defend against…
Diffusion models have achieved notable success in image generation, but they remain highly vulnerable to backdoor attacks, which compromise their integrity by producing specific undesirable outputs when presented with a pre-defined trigger.…
Safeguarding intellectual property and preventing potential misuse of AI-generated images are of paramount importance. This paper introduces a robust and agile plug-and-play watermark detection framework, dubbed as RAW. As a departure from…
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…
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio. Due to their adaptiveness in iterative refinement, they provide a strong potential for achieving better non-autoregressive…
Diffusion models (DMs) have demonstrated advantageous potential on generative tasks. Widespread interest exists in incorporating DMs into downstream applications, such as producing or editing photorealistic images. However, practical…
Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…
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…
Machine learning models are being used in an increasing number of critical applications; thus, securing their integrity and ownership is critical. Recent studies observed that adversarial training and watermarking have a conflicting…
LLMs now exhibit human-like skills in various fields, leading to worries about misuse. Thus, detecting generated text is crucial. However, passive detection methods are stuck in domain specificity and limited adversarial robustness. To…
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…
Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through black-box queries. Model watermarking counters MEAs by…
We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…
Nowadays, it is common to release audio content to the public. However, with the rise of voice cloning technology, attackers have the potential to easily impersonate a specific person by utilizing his publicly released audio without any…
Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bit watermarking systems lack the capacity for large-scale…