相关论文: Local Aggressive Adversarial Attacks on 3D Point C…

Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images. These perturbed images are known as `adversarial examples' and pose a serious threat to security and safety critical systems. A…

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…

Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…

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…

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification…

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

Recently, 3D backdoor attacks have posed a substantial threat to 3D Deep Neural Networks (3D DNNs) designed for 3D point clouds, which are extensively deployed in various security-critical applications. Although the existing 3D backdoor…

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…

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…

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,…

For relocalization in large-scale point clouds, we propose the first approach that unifies global place recognition and local 6DoF pose refinement. To this end, we design a Siamese network that jointly learns 3D local feature detection and…

Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to…

Most autonomous vehicles (AVs) rely on LiDAR and RGB camera sensors for perception. Using these point cloud and image data, perception models based on deep neural nets (DNNs) have achieved state-of-the-art performance in 3D detection. The…

Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…

In recent years, deep neural networks demonstrated state-of-the-art performance in a large variety of tasks and therefore have been adopted in many applications. On the other hand, the latest studies revealed that neural networks are…

The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…

This paper proposes an adaptive margin contrastive learning method for 3D semantic segmentation on point clouds. Most existing methods use equally penalized objectives, which ignore the per-point ambiguities and less discriminated features…

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image,…

2D face recognition has been proven insecure for physical adversarial attacks. However, few studies have investigated the possibility of attacking real-world 3D face recognition systems. 3D-printed attacks recently proposed cannot generate…