Related papers: Towards A Correct Usage of Cryptography in Semanti…
With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope…
Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…
Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe risks of unauthorized use. Although digital watermarking…
The effectiveness of watermark algorithms in AI-generated text identification has garnered significant attention. Concurrently, an increasing number of watermark algorithms have been proposed to enhance the robustness against various…
Robust invisible watermarking schemes aim to embed hidden information into images such that the watermark survives common manipulations. However, powerful diffusion-based image generation and editing techniques now pose a new threat to…
Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the API misuse and model extraction attacks. Various studies have…
We propose a general method for semantic representation of images and other data using progressive coding. Semantic coding allows for specific pieces of information to be selectively encoded into a set of measurements that can be highly…
In the audio modality, state-of-the-art watermarking methods leverage deep neural networks to allow the embedding of human-imperceptible signatures in generated audio. The ideal is to embed signatures that can be detected with high accuracy…
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…
We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the watermark directly into the learned continuous dynamics -- the velocity field of a flow…
Generative models have enabled easy creation and generation of images of all kinds given a single prompt. However, this has also raised ethical concerns about what is an actual piece of content created by humans or cameras compared to…
We introduce the zero-sum game problem of soft watermarking: The hidden information (watermark) comes from a continuum and has a perceptual value; the receiver generates an estimate of the embedded watermark to minimize the expected…
Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in both image and audio domains. In the rapidly evolving field…
Existing approaches for watermarking AI-generated images often rely on post-hoc methods applied in pixel space, introducing computational overhead and potential visual artifacts. In this work, we explore latent space watermarking and…
Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection. While token-level watermarks are vulnerable to paraphrase attacks, SemStamp (Hou et al., 2023) applies…
This paper introduces a new watermarking algorithm based on discrete chaotic iterations. After defining some coefficients deduced from the description of the carrier medium, chaotic discrete iterations are used to mix the watermark and to…
Watermarking embeds imperceptible patterns into images for authenticity verification. However, existing methods often lack robustness against various transformations primarily including distortions, image regeneration, and adversarial…
Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive…
The rapid adoption of diffusion-based generative models has intensified concerns over the attribution and integrity of AI-generated content (AIGC). Existing single-domain watermarking methods either fail under regeneration, remain…
Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…