Related papers: Towards More Realistic Membership Inference Attack…

Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial…

Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Recently proposed large-scale text-to-image generative models such as DALL$\cdot$E 2, Midjourney, and StableDiffusion can generate high-quality and realistic images from users' prompts. Not limited to the research community, ordinary…

Generative models have seen an explosion in popularity with the release of huge generative Diffusion models like Midjourney and Stable Diffusion to the public. Because of this new ease of access, questions surrounding the automated…

Image classification systems often inherit biases from uneven group representation in training data. For example, in face datasets for hair color classification, blond hair may be disproportionately associated with females, reinforcing…

We fine-tuned a foundational stable diffusion model using X-ray scattering images and their corresponding descriptions to generate new scientific images from given prompts. However, some of the generated images exhibit significant…

The evolution of artificial intelligence (AI) has catalyzed a transformation in digital content generation, with profound implications for cyber influence operations. This report delves into the potential and limitations of generative deep…

This paper explores the task of detecting images generated by text-to-image diffusion models. To evaluate this, we consider images generated from captions in the MSCOCO and Wikimedia datasets using two state-of-the-art models: Stable…

Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them…

Diffusion models excel in many generative modeling tasks, notably in creating images from text prompts, a task referred to as text-to-image (T2I) generation. Despite the ability to generate high-quality images, these models often replicate…

Nowadays, the development of a Presentation Attack Detection (PAD) system for ID cards presents a challenge due to the lack of images available to train a robust PAD system and the increase in diversity of possible attack instrument…

Recently, there has been significant progress in the development of large models. Following the success of ChatGPT, numerous language models have been introduced, demonstrating remarkable performance. Similar advancements have also been…

Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that ML models are vulnerable to attacks against their training…

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…

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 rapid progress in generative models has given rise to the critical task of AI-Generated Content Stealth (AIGC-S), which aims to create AI-generated images that can evade both forensic detectors and human inspection. This task is crucial…

Generative models have increasingly impacted various tasks, from computer vision to interior design and beyond. Stable Diffusion, a powerful diffusion model, enables the creation of high-resolution images with intricate details from text…

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…