相关论文: NoPain: No-box Point Cloud Attack via Optimal Tran…

Deep neural networks have been widely used in various downstream tasks, especially those safety-critical scenario such as autonomous driving, but deep networks are often threatened by adversarial samples. Such adversarial attacks can be…

Deep neural networks are vulnerable to adversarial examples, which are crafted by applying small, human-imperceptible perturbations on the original images, so as to mislead deep neural networks to output inaccurate predictions. Adversarial…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

This work extends our prior work on the distributed nonlinear model predictive control (NMPC) for navigating a robot fleet following a certain flocking behavior in unknown obstructed environments with a more realistic local obstacle…

Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the…

Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected…

In point cloud compression, sufficient contexts are significant for modeling the point cloud distribution. However, the contexts gathered by the previous voxel-based methods decrease when handling sparse point clouds. To address this…

Deep neural networks for image classification remain vulnerable to adversarial examples -- small, imperceptible perturbations that induce misclassifications. In black-box settings, where only the final prediction is accessible, crafting…

Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoising are typical strategies for defending adversarial…

In this work we propose Energy Attack, a transfer-based black-box $L_\infty$-adversarial attack. The attack is parameter-free and does not require gradient approximation. In particular, we first obtain white-box adversarial perturbations of…

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, posing significant security threats to their deployment in remote sensing applications. Research on adversarial attacks not only reveals model vulnerabilities but also…

With the maturity of depth sensors, point clouds have received increasing attention in various applications such as autonomous driving, robotics, surveillance, etc., while deep point cloud learning models have shown to be vulnerable to…

Though deep neural networks perform challenging tasks excellently, they are susceptible to adversarial examples, which mislead classifiers by applying human-imperceptible perturbations on clean inputs. Under the query-free black-box…

Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing…

Evasion Attacks (EA) are used to test the robustness of trained neural networks by distorting input data to misguide the model into incorrect classifications. Creating these attacks is a challenging task, especially with the ever-increasing…

Despite the improved accuracy of deep neural networks, the discovery of adversarial examples has raised serious safety concerns. Most existing approaches for crafting adversarial examples necessitate some knowledge (architecture,…

Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities. Without any additional structural assumptions on trans-port, however, OT can…

Although adversarial robustness has been extensively studied in white-box settings, recent advances in black-box attacks (including transfer- and query-based approaches) are primarily benchmarked against weak defenses, leaving a significant…

Many studies have been done to prove the vulnerability of neural networks to adversarial example. A trained and well-behaved model can be fooled by a visually imperceptible perturbation, i.e., an originally correctly classified image could…