相关论文: High-Frequency Anti-DreamBooth: Robust Defense aga…

The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on social media. Several attempts have been made to protect…

Recently, zero-shot methods like InstantID have revolutionized identity-preserving generation. Unlike multi-image finetuning approaches such as DreamBooth, these zero-shot methods leverage powerful facial encoders to extract identity…

The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker's intent to…

The rapid growth of social media has led to the widespread sharing of individual portrait images, which pose serious privacy risks due to the capabilities of automatic face recognition (AFR) systems for mass surveillance. Hence, protecting…

In order to prevent illegal or unauthorized access of image data such as human faces and ensure legitimate users can use authorization-protected data, reversible adversarial attack technique is rise. Reversible adversarial examples (RAE)…

This paper presents a novel method to deal with the challenging task of generating photographic images conditioned on semantic image descriptions. Our method introduces accompanying hierarchical-nested adversarial objectives inside the…

Deep Learning models are highly susceptible to adversarial manipulations that can lead to catastrophic consequences. One of the most effective methods to defend against such disturbances is adversarial training but at the cost of…

Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…

Universal Adversarial Perturbations are image-agnostic and model-independent noise that when added with any image can mislead the trained Deep Convolutional Neural Networks into the wrong prediction. Since these Universal Adversarial…

Stable Diffusion has established itself as a foundation model in generative AI artistic applications, receiving widespread research and application. Some recent fine-tuning methods have made it feasible for individuals to implant…

Physical adversarial patches printed on clothing can enable individuals to evade person detectors, but most existing methods prioritize attack effectiveness over stealthiness, resulting in aesthetically unpleasing patches. While generative…

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

In this paper, we focus on generating realistic images from text descriptions. Current methods first generate an initial image with rough shape and color, and then refine the initial image to a high-resolution one. Most existing…

Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on…

This work presents an end-to-end pipeline for generating, refining, and evaluating adversarial patches to compromise facial biometric systems, with applications in forensic analysis and security testing. We utilize FGSM to generate…

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Adversarial attacks find perturbations that can fool models into misclassifying images. Previous works had successes in generating noisy/edge-rich adversarial perturbations, at the cost of degradation of image quality. Such perturbations,…

A plethora of recent work has shown that convolutional networks are not robust to adversarial images: images that are created by perturbing a sample from the data distribution as to maximize the loss on the perturbed example. In this work,…

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…