Related papers: Provably Secure Covert Messaging Using Image-based…
Recently large-scale language-image models (e.g., text-guided diffusion models) have considerably improved the image generation capabilities to generate photorealistic images in various domains. Based on this success, current image editing…
Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image quality usually…
Hiding data using neural networks (i.e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks. However, the potential of data hiding in diffusion models remains…
The success of recent text-to-image diffusion models is largely due to their capacity to be guided by a complex text prompt, which enables users to precisely describe the desired content. However, these models struggle to effectively…
Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images or compressed images…
Robust steganography is a technique of hiding secret messages in images so that the message can be recovered after additional image processing. One of the most popular processing operations is JPEG recompression. Unfortunately, most of…
Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos…
Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…
The past few years have witnessed substantial advances in image generation powered by diffusion models. However, it was shown that diffusion models are susceptible to training data memorization, raising significant concerns regarding…
There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate…
We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to…
Diffusion models have been widely deployed in various image generation tasks, demonstrating an extraordinary connection between image and text modalities. Although prior studies have explored the vulnerability of diffusion models from the…
Diffusion-based text-to-image generation models trade latency for quality: small models are fast but generate lower-quality images, while large models produce better images but are slow. We present MoDM, a novel caching-based serving system…
Diffusion models are a remarkably effective way of learning and sampling from a distribution $p(x)$. In posterior sampling, one is also given a measurement model $p(y \mid x)$ and a measurement $y$, and would like to sample from $p(x \mid…
An important problem of reconstruction of diffusion network and transmission probabilities from the data has attracted a considerable attention in the past several years. A number of recent papers introduced efficient algorithms for the…
Diffusion models have demonstrated significant promise in various generative tasks; however, they often struggle to satisfy challenging constraints. Our approach addresses this limitation by rethinking training-free loss-guided diffusion…
I study a model of information acquisition and transmission in which the sender's ability to misreport her findings is limited. The sender learns covertly, so a key observation is that in equilibrium she must be deterred from undetectably…
Adversarial examples for diffusion models are widely used as solutions for safety concerns. By adding adversarial perturbations to personal images, attackers can not edit or imitate them easily. However, it is essential to note that all…
Diffusion models have shown an impressive ability to model complex data distributions, with several key advantages over GANs, such as stable training, better coverage of the training distribution's modes, and the ability to solve inverse…
An information is a message which is received and understood. Information can be sent one person to another over a long range but the process of sending information must be done in a secure way especially in case of a private message.…