Related papers: Towards More Realistic Membership Inference Attack…

With the help of conditioning mechanisms, the state-of-the-art diffusion models have achieved tremendous success in guided image generation, particularly in text-to-image synthesis. To gain a better understanding of the training process and…

Despite their remarkable image generation capabilities, text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data, which leads to various ethical and business risks. Specifically,…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to address both…

A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training data. Most MI research focuses on the case of a single…

Robust invisible watermarking aims to embed hidden messages into images such that they survive various manipulations while remaining imperceptible. However, powerful diffusion-based image generation and editing models now enable realistic…

Membership inference attacks allow a malicious entity to predict whether a sample is used during training of a victim model or not. State-of-the-art membership inference attacks have shown to achieve good accuracy which poses a great…

Stable Diffusion is a popular Transformer-based model for image generation from text; it applies an image information creator to the input text and the visual knowledge is added in a step-by-step fashion to create an image that corresponds…

Generating high-quality labeled image datasets is crucial for training accurate and robust machine learning models in the field of computer vision. However, the process of manually labeling real images is often time-consuming and costly. To…

Cybersecurity practices require effort to be maintained, and one weakness is a lack of awareness regarding potential attacks not only in the usage of machine learning models, but also in their development process. Previous studies have…

Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has…

Generative foundation models like Stable Diffusion comprise a diverse spectrum of knowledge in computer vision with the potential for transfer learning, e.g., via generating data to train student models for downstream tasks. This could…

Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…

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…

Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition. The image encoder pre-trained through MIM, involving the masking and subsequent reconstruction of input…

In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as…

In this work, we propose a set-membership inference attack for generative models using deep image watermarking techniques. In particular, we demonstrate how conditional sampling from a generative model can reveal the watermark that was…

Diffusion models have demonstrated significant potential in image generation. However, their ability to replicate training data presents a privacy risk, particularly when the training data includes confidential information. Existing…

The proliferation of large language models (LLMs) in the real world has come with a rise in copyright cases against companies for training their models on unlicensed data from the internet. Recent works have presented methods to identify if…

Recent image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a simple text prompt. Could such models render real images obsolete for training image prediction…

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…