Related papers: Finding Optimal Tangent Points for Reducing Distor…
Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Existing class-wise targeted attacks remain impractical for stealthy exploitation in this…
Adversarial examples are known as carefully perturbed images fooling image classifiers. We propose a geometric framework to generate adversarial examples in one of the most challenging black-box settings where the adversary can only…
We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…
Adversarial attacks pose a significant threat to machine learning models by inducing incorrect predictions through imperceptible perturbations to input data. While these attacks are well studied in unstructured domains such as images, their…
Deep neural networks are vulnerable to adversarial attacks. Among different attack settings, the most challenging yet the most practical one is the hard-label setting where the attacker only has access to the hard-label output (prediction…
We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a…
Adversarial attacks are a central tool for probing the robustness of modern vision models, yet most methods optimize perturbations directly in pixel space under $\ell_\infty$ or $\ell_2$ constraints. While effective in white-box settings,…
With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the…
One of the most practical and challenging types of black-box adversarial attacks is the hard-label attack, where only the top-1 predicted label is available. One effective approach is to search for the optimal ray direction from the benign…
Deep recognition models are widely vulnerable to adversarial examples, which change the model output by adding quasi-imperceptible perturbation to the image input. Recently, Segment Anything Model (SAM) has emerged to become a popular…
Generating adversarial examples in a black-box setting retains a significant challenge with vast practical application prospects. In particular, existing black-box attacks suffer from the need for excessive queries, as it is non-trivial to…
A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute models to generate the perturbation, then apply the…
In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to practical deployment. In this paper, we focus on optimizing a representative class…
Adversarial training has proven effective in improving the robustness of deep neural networks against adversarial attacks. However, this enhanced robustness often comes at the cost of a substantial drop in accuracy on clean data. In this…
Existing score-based adversarial attacks mainly focus on crafting $top$-1 adversarial examples against classifiers with single-label classification. Their attack success rate and query efficiency are often less than satisfactory,…
Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…
Decision-based attacks (DBA), wherein attackers perturb inputs to spoof learning algorithms by observing solely the output labels, are a type of severe adversarial attacks against Deep Neural Networks (DNNs) requiring minimal knowledge of…
Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…
We propose a novel framework for real-time black-box universal attacks which disrupts activations of early convolutional layers in deep learning models. Our hypothesis is that perturbations produced in the wavelet space disrupt early…