Related papers: Controllable Adversarial Makeup for Privacy via Te…

Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection. Existing adversarial perturbations-based methods mainly focus on the de-identification against…

Face anti-spoofing (FAS) plays a vital role in preventing face recognition (FR) systems from presentation attacks. Nowadays, FAS systems face the challenge of domain shift, impacting the generalization performance of existing FAS methods.…

Human facial images encode a rich spectrum of information, encompassing both stable identity-related traits and mutable attributes such as pose, expression, and emotion. While recent advances in image generation have enabled high-quality…

Adversarial attacks meticulously generate minuscule, imperceptible perturbations to images to deceive neural networks. Counteracting these, adversarial purification methods seek to transform adversarial input samples into clean output…

Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. These methods do not make assumptions on the form of attack and the classification model, and thus can defend…

Diffusion-based personalized visual content generation technologies have achieved significant breakthroughs, allowing for the creation of specific objects by just learning from a few reference photos. However, when misused to fabricate fake…

Diffusion-based inpainting is a powerful tool for the reconstruction of images from sparse data. Its quality strongly depends on the choice of known data. Optimising their spatial location -- the inpainting mask -- is challenging. A…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…

Self-supervised representation learning has gained increasing attention for strong generalization ability without relying on paired datasets. However, it has not been explored sufficiently for facial representation. Self-supervised facial…

Adversarial training is a common strategy for enhancing model robustness against adversarial attacks. However, it is typically tailored to the specific attack types it is trained on, limiting its ability to generalize to unseen threat…

Nowadays, cameras equipped with AI systems can capture and analyze images to detect people automatically. However, the AI system can make mistakes when receiving deliberately designed patterns in the real world, i.e., physical adversarial…

Monocular Depth Estimation (MDE) serves as a core perception module in autonomous driving systems, but it remains highly susceptible to adversarial attacks. Errors in depth estimation may propagate through downstream decision making and…

With the progress in AI-based facial forgery (i.e., deepfake), people are increasingly concerned about its abuse. Albeit effort has been made for training classification (also known as deepfake detection) models to recognize such forgeries,…

Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking…

Personalized AI applications such as DreamBooth enable the generation of customized content from user images, but also raise significant privacy concerns, particularly the risk of facial identity leakage. Recent defense mechanisms like…

Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned…

Existing diffusion-based purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples. However, this…

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…

In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models…