Related papers: Hide in Thicket: Generating Imperceptible and Rati…
Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have…
With the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of point cloud networks by…
Recent studies have revealed that vision transformers (ViTs) face similar security risks from adversarial attacks as deep convolutional neural networks (CNNs). However, directly applying attack methodology on CNNs to ViTs has been…
Monocular 3D object detection plays a pivotal role in the field of autonomous driving and numerous deep learning-based methods have made significant breakthroughs in this area. Despite the advancements in detection accuracy and efficiency,…
Machine learning models have been shown vulnerable to adversarial attacks launched by adversarial examples which are carefully crafted by attacker to defeat classifiers. Deep learning models cannot escape the attack either. Most of…
The advent of deep neural networks has led to remarkable progress in 3D point cloud recognition, but they remain vulnerable to adversarial attacks. Although various defense methods have been studied, they suffer from a trade-off between…
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…
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…
Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to…
We investigate the role of representations and architectures for classifying 3D shapes in terms of their computational efficiency, generalization, and robustness to adversarial transformations. By varying the number of training examples and…
Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense…
In this paper, we propose a defence strategy to improve adversarial robustness by incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input information including adversarial perturbation.…
Intermediate-level attacks that attempt to perturb feature representations following an adversarial direction drastically have shown favorable performance in crafting transferable adversarial examples. Existing methods in this category are…
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…
Visual recognition models are not invariant to viewpoint changes in the 3D world, as different viewing directions can dramatically affect the predictions given the same object. Although many efforts have been devoted to making neural…
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…
Deep learning has achieved remarkable success in direction-of-arrival (DOA) estimation. However, recent studies have shown that adversarial perturbations can severely compromise the performance of such models. To address this vulnerability,…
Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While these carefully crafted perturbations restricted with tight…
Face recognition is a prevailing authentication solution in numerous biometric applications. Physical adversarial attacks, as an important surrogate, can identify the weaknesses of face recognition systems and evaluate their robustness…
Recent progress in adversarial attacks on 3D point clouds, particularly in achieving spatial imperceptibility and high attack performance, presents significant challenges for defenders. Current defensive approaches remain cumbersome, often…