相关论文: LaWa: Using Latent Space for In-Generation Image W…

Large-scale 3D generative models require substantial computational resources yet often fall short in capturing fine details and complex geometries at high resolutions. We attribute this limitation to the inefficiency of current…

Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…

Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorithms (SWAs) derive watermark information from watermarked…

We propose a watermarking method for protecting the Intellectual Property (IP) of Generative Adversarial Networks (GANs). The aim is to watermark the GAN model so that any image generated by the GAN contains an invisible watermark…

Recently, stable diffusion (SD) models have typically flourished in the field of image synthesis and personalized editing, with a range of photorealistic and unprecedented images being successfully generated. As a result, widespread…

The proliferation of autoregressive (AR) image generators demands reliable detection and attribution of their outputs to mitigate misinformation, and to filter synthetic images from training data to prevent model collapse. To address this…

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…

Invisible watermarking for autoregressive (AR) image generation has recently gained attention as a means of protecting image ownership and tracing AI-generated content. However, existing approaches suffer from three key limitations: (1)…

Watermarking has become a key technique for proprietary language models, enabling the distinction between AI-generated and human-written text. However, in many real-world scenarios, LLM-generated content may undergo post-generation edits,…

Deepfakes refer to content synthesized using deep generators, which, when misused, have the potential to erode trust in digital media. Synthesizing high-quality deepfakes requires access to large and complex generators only a few entities…

Protecting deep neural networks (DNNs) against intellectual property (IP) infringement has attracted an increasing attention in recent years. Recent advances focus on IP protection of generative models, which embed the watermark information…

Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming…

Generative AI has demonstrated significant potential in creative design, enabling the rapid generation of visual content and imaginative concepts. Although deep AI models achieve effective featurization in the latent space, navigating the…

Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving remarkable progress across various tasks, such as image and…

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

Digital watermarks can be embedded into AI-generated content (AIGC) by initializing the generation process with starting points sampled from a secret distribution. When combined with pseudorandom error-correcting codes, such watermarked…

Latent Diffusion Models (LDM), a subclass of diffusion models, mitigate the computational complexity of pixel-space diffusion by operating within a compressed latent space constructed by Variational Autoencoders (VAEs), demonstrating…

With the increasing attention to deep neural network (DNN) models, attacks are also upcoming for such models. For example, an attacker may carefully construct images in specific ways (also referred to as adversarial examples) aiming to…

The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking, embedding a signature into the generative model's synthesis…

Despite recent advances in semantic manipulation using StyleGAN, semantic editing of real faces remains challenging. The gap between the $W$ space and the $W$+ space demands an undesirable trade-off between reconstruction quality and…