Related papers: Physically Realizable Adversarial Examples for LiD…

This paper presents a novel framework for robust 3D object detection from point clouds via cross-modal hallucination. Our proposed approach is agnostic to either hallucination direction between LiDAR and 4D radar. We introduce multiple…

3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a…

Deep neural networks (DNNs) are vulnerable to adversarial examples-maliciously crafted inputs that cause DNNs to make incorrect predictions. Recent work has shown that these attacks generalize to the physical domain, to create perturbations…

Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against MDE models rely on 2D adversarial patches, so they only…

Recent developments and the beginning market introduction of high-resolution imaging 4D (3+1D) radar sensors have initialized deep learning-based radar perception research. We investigate deep learning-based models operating on radar point…

Recent studies reveal that deep neural network (DNN) based object detectors are vulnerable to adversarial attacks in the form of adding the perturbation to the images, leading to the wrong output of object detectors. Most current existing…

We present a system for automatic converting of 2D mask object predictions and raw LiDAR point clouds into full 3D bounding boxes of objects. Because the LiDAR point clouds are partial, directly fitting bounding boxes to the point clouds is…

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…

It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image space may cause a trained neural network model to misclassify…

Autonomous vehicles (AVs) rely on complex perception and communication systems, making them vulnerable to adversarial attacks that can compromise safety. While simulation offers a scalable and safe environment for robustness testing,…

In adversarial attacks intended to confound deep learning models, most studies have focused on limiting the magnitude of the modification so that humans do not notice the attack. On the other hand, during an attack against autonomous cars,…

Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings.…

Neural networks build the foundation of several intelligent systems, which, however, are known to be easily fooled by adversarial examples. Recent advances made these attacks possible even in air-gapped scenarios, where the autonomous…

LiDAR sensors are used in autonomous driving applications to accurately perceive the environment. However, they are affected by adverse weather conditions such as snow, fog, and rain. These everyday phenomena introduce unwanted noise into…

In the last few years, the scientific community showed a remarkable and increasing interest towards 3D Virtual Environments, training and testing Machine Learning-based models in realistic virtual worlds. On one hand, these environments…

3D deep models consuming point clouds have achieved sound application effects in computer vision. However, recent studies have shown they are vulnerable to 3D adversarial point clouds. In this paper, we regard these malicious point clouds…

We introduce ShapeAdv, a novel framework to study shape-aware adversarial perturbations that reflect the underlying shape variations (e.g., geometric deformations and structural differences) in the 3D point cloud space. We develop…

Most real-world 3D sensors such as LiDARs perform fixed scans of the entire environment, while being decoupled from the recognition system that processes the sensor data. In this work, we propose a method for 3D object recognition using…

Deep learning-based systems have been shown to be vulnerable to adversarial attacks in both digital and physical domains. While feasible, digital attacks have limited applicability in attacking deployed systems, including face recognition…

Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection. Existing adversarial perturbations-based methods mainly focus on the de-identification against…