相关论文: BlackMirror: Black-Box Backdoor Detection for Text…

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1) Semantic Consistency, where backdoor prompts tend to…

Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generation of offensive content. Image Generation Model Unlearning…

The increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations, highlighting the urgent need for accurate and interpretable detection methods. While existing approaches have made…

Deep regression models are used in a wide variety of safety-critical applications, but are vulnerable to backdoor attacks. Although many defenses have been proposed for classification models, they are ineffective as they do not consider the…

Despite the growing popularity of modern machine learning techniques (e.g. Deep Neural Networks) in cyber-security applications, most of these models are perceived as a black-box for the user. Adversarial machine learning offers an approach…

Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However, they are vulnerable to backdoor attacks as reported by…

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed…

Machine-learning models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as…

Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the…

We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation method exploits the latent feature space learned through an adversarial autoencoder.…

Vision-Language models like CLIP have been shown to be highly effective at linking visual perception and natural language understanding, enabling sophisticated image-text capabilities, including strong retrieval and zero-shot classification…

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of…

Foundation models have revolutionized computer vision by enabling broad generalization across diverse tasks. Yet, they remain highly susceptible to adversarial perturbations and targeted backdoor attacks. Mitigating such vulnerabilities…

Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs via covert triggers embedded in inputs. Existing defenses,…

Reference-based image super-resolution (RefSR) represents a promising advancement in super-resolution (SR). In contrast to single-image super-resolution (SISR), RefSR leverages an additional reference image to help recover high-frequency…

We study the task of replicating the functionality of black-box neural models, for which we only know the output class probabilities provided for a set of input images. We assume back-propagation through the black-box model is not possible…

Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be easily countered by…

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…