相关论文: Diffusion Models for Adversarial Purification

Diffusion models have revolutionized generative modeling with their exceptional ability to produce high-fidelity images. However, misuse of such potent tools can lead to the creation of fake news or disturbing content targeting individuals,…

Diffusion models have gained significant attention for high-fidelity image generation. Our work investigates the potential of exploiting diffusion models for adversarial robustness in image classification and object detection. Adversarial…

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

Neural networks have revolutionized numerous fields with their exceptional performance, yet they remain susceptible to adversarial attacks through subtle perturbations. While diffusion-based purification methods like DiffPure offer…

Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a more thorough examination of potential security flaws before…

Denoising Diffusion Probabilistic Models (DDPMs) have gained great attention in adversarial purification. Current diffusion-based works focus on designing effective condition-guided mechanisms while ignoring a fundamental problem, i.e., the…

Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial…

Deep neural networks are known to be vulnerable to well-designed adversarial attacks. Although numerous defense strategies have been proposed, many are tailored to the specific attacks or tasks and often fail to generalize across diverse…

Recognizing 3D point cloud plays a pivotal role in many real-world applications. However, deploying 3D point cloud deep learning model is vulnerable to adversarial attacks. Despite many efforts into developing robust model by adversarial…

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this…

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored…

Diffusion Probabilistic Models (DPMs) have emerged as a powerful class of deep generative models, achieving remarkable performance in image synthesis tasks. However, these models face challenges in terms of widespread adoption due to their…

Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails…

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…

Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generating realistic details, and ensuring pixel-level consistency.…

From its acquisition in the camera sensors to its storage, different operations are performed to generate the final image. This pipeline imprints specific traces into the image to form a natural watermark. Tampering with an image disturbs…

Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods…

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…

Adversarial purification with diffusion models seeks to project adversarial examples back toward the data manifold, but balancing semantic preservation and robustness against adaptive attacks remains challenging. Recent work shows that…