Related papers: Classifier Guidance Enhances Diffusion-based Adver…

Deep Neural Networks (DNNs) are known to be vulnerable to both backdoor and adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct robustness problems and solved separately, since they belong to…

Given a black-box classification model and an unlabeled evaluation dataset from some application domain, efficient strategies need to be developed to evaluate the model. Random sampling allows a user to estimate metrics like accuracy,…

To ensure that the data collected from human subjects is entrusted with a secret, rival labels are introduced to conceal the information provided by the participants on purpose. The corresponding learning task can be formulated as a noisy…

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

With the widespread use of online social media platforms, information diffusion has become a prevalent phenomenon, making Information Diffusion Prediction (IDP) increasingly important for various applications. Despite significant…

Recently, text-to-image generative models have been misused to create unauthorized malicious images of individuals, posing a growing social problem. Previous solutions, such as Anti-DreamBooth, add adversarial noise to images to protect…

We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur $\it{unintentionally}$ ("natural errors"), or due to…

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Diffusion models (DMs) have demonstrated great potential in the field of adversarial robustness, where DM-based defense methods can achieve superior defense capability without adversarial training. However, they all require huge…

Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we…

Denoising diffusion models have shown remarkable potential in various generation tasks. The open-source large-scale text-to-image model, Stable Diffusion, becomes prevalent as it can generate realistic artistic or facial images with…

Adversarial training improves the robustness of neural networks against adversarial attacks, albeit at the expense of the trade-off between standard and robust generalization. To unveil the underlying factors driving this phenomenon, we…

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence…

In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models. To do so, we instantiate the denoised smoothing approach of…

This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and making use of the duality between network weights and layer…

Diffusion models learn to denoise data and the trained denoiser is then used to generate new samples from the data distribution. In this paper, we revisit the diffusion sampling process and identify a fundamental cause of sample quality…

As face recognition becomes more widespread in government and commercial services, its potential misuse raises serious concerns about privacy and civil rights. To counteract this threat, various anti-facial recognition techniques have been…

Deep Neural Networks (DNNs) are vulnerable to adversarial examples generated by imposing subtle perturbations to inputs that lead a model to predict incorrect outputs. Currently, a large number of researches on defending adversarial…

Diffusion Purification, purifying noised images with diffusion models, has been widely used for enhancing certified robustness via randomized smoothing. However, existing frameworks often grapple with the balance between efficiency and…

In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…