Related papers: AEGIS: Adversarial Target-Guided Retention-Data-Fr…

Deep networks for computer vision are not reliable when they encounter adversarial examples. In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference. By introducing…

Multi-modal foundation models align images, text, and other modalities in a shared embedding space but remain vulnerable to adversarial illusions [35], where imperceptible perturbations disrupt cross-modal alignment and mislead downstream…

The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine unlearning (MU) -- commonly referred to as concept erasure…

Synthetic data generation has become an emerging tool to help improve the adversarial robustness in classification tasks since robust learning requires a significantly larger amount of training samples compared with standard classification…

Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting…

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

Cloud removal (CR) remains a challenging task in remote sensing image processing. Although diffusion models (DM) exhibit strong generative capabilities, their direct applications to CR are suboptimal, as they generate cloudless images from…

Recent advancements in generative AI, particularly diffusion-based image editing, have enabled the transformation of images into highly realistic scenes using only text instructions. This technology offers significant potential for…

Remote sensing change detection between bi-temporal images receives growing concentration from researchers. However, comparing two bi-temporal images for detecting changes is challenging, as they demonstrate different appearances. In this…

Image Quality Assessment (IQA) models are increasingly relied upon to evaluate image quality in real-world systems -- from compression and enhancement to generation and streaming. Yet their adoption brings a fundamental risk: these models…

Rapid advances in Artificial Intelligence Generated Images (AIGI) have facilitated malicious use, such as forgery and misinformation. Therefore, numerous methods have been proposed to detect fake images. Although such detectors have been…

Robustness of deep learning models is a property that has recently gained increasing attention. We explore a notion of robustness for generative adversarial models that is pertinent to their internal interactive structure, and show that,…

Existing segmentation models exhibit significant vulnerability to adversarial attacks.To improve robustness, adversarial training incorporates adversarial examples into model training. However, existing attack methods consider only global…

The introduction of robust optimisation has pushed the state-of-the-art in defending against adversarial attacks. Notably, the state-of-the-art projected gradient descent (PGD)-based training method has been shown to be universally and…

The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by…

Adversarial robustness has been conventionally believed as a challenging property to encode for neural networks, requiring plenty of training data. In the recent paradigm of adopting off-the-shelf models, however, access to their training…

The remarkable development of text-to-image generation models has raised notable security concerns, such as the infringement of portrait rights and the generation of inappropriate content. Concept erasure has been proposed to remove the…

Image Generation models are a trending topic nowadays, with many people utilizing Artificial Intelligence models in order to generate images. There are many such models which, given a prompt of a text, will generate an image which depicts…

Achieving resiliency against adversarial attacks is necessary prior to deploying neural network classifiers in domains where misclassification incurs substantial costs, e.g., self-driving cars or medical imaging. Recent work has…

In the classic machine learning framework, models are trained on historical data and used to predict future values. It is assumed that the data distribution does not change over time (stationarity). However, in real-world scenarios, the…