A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks

• URL: http://arxiv.org/abs/2212.10230v3
• Date: Tue, 17 Oct 2023 13:14:03 GMT
• Title: A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks
• Authors: Yifan Zhang, Junhui Hou, Yixuan Yuan
• Abstract summary: 3D object detectors are increasingly crucial for security-critical tasks. It is imperative to understand their robustness against adversarial attacks. This paper presents the first comprehensive evaluation and analysis of the robustness of LiDAR-based 3D detectors under adversarial attacks.
• Score: 84.10546708708554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent years have witnessed significant advancements in deep learning-based 3D object detection, leading to its widespread adoption in numerous applications. As 3D object detectors become increasingly crucial for security-critical tasks, it is imperative to understand their robustness against adversarial attacks. This paper presents the first comprehensive evaluation and analysis of the robustness of LiDAR-based 3D detectors under adversarial attacks. Specifically, we extend three distinct adversarial attacks to the 3D object detection task, benchmarking the robustness of state-of-the-art LiDAR-based 3D object detectors against attacks on the KITTI and Waymo datasets. We further analyze the relationship between robustness and detector properties. Additionally, we explore the transferability of cross-model, cross-task, and cross-data attacks. Thorough experiments on defensive strategies for 3D detectors are conducted, demonstrating that simple transformations like flipping provide little help in improving robustness when the applied transformation strategy is exposed to attackers. \revise{Finally, we propose balanced adversarial focal training, based on conventional adversarial training, to strike a balance between accuracy and robustness.} Our findings will facilitate investigations into understanding and defending against adversarial attacks on LiDAR-based 3D object detectors, thus advancing the field. The source code is publicly available at \url{https://github.com/Eaphan/Robust3DOD}.

Related papers

• ScAR: Scaling Adversarial Robustness for LiDAR Object Detection [6.472434306724611]
  Adversarial robustness of a model is its ability to resist adversarial attacks. We present a black-box scaling adversarial attack method for LiDAR object detection.
  arXiv  Detail & Related papers  (2023-12-05T19:03:33Z)
• AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Training [64.14759275211115]
  We propose a depth-aware robust adversarial training method for monocular 3D object detection, dubbed DART3D. Our adversarial training approach capitalizes on the inherent uncertainty, enabling the model to significantly improve its robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2023-09-03T07:05:32Z)
• On the Adversarial Robustness of Camera-based 3D Object Detection [21.091078268929667]
  We investigate the robustness of leading camera-based 3D object detection approaches under various adversarial conditions. We find that bird's-eye-view-based representations exhibit stronger robustness against localization attacks. depth-estimation-free approaches have the potential to show stronger robustness. incorporating multi-frame benign inputs can effectively mitigate adversarial attacks.
  arXiv  Detail & Related papers  (2023-01-25T18:59:15Z)
• Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training [57.25828870799331]
  We propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D. We develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain. STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.
  arXiv  Detail & Related papers  (2022-04-25T12:23:07Z)
• Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models [16.823829387723524]
  We analyze the robustness of a high-performance, open source sensor fusion model architecture towards adversarial attacks. We find that despite the use of a LIDAR sensor, the model is vulnerable to our purposefully crafted image-based adversarial attacks.
  arXiv  Detail & Related papers  (2021-09-13T23:38:42Z)
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection [78.71826145162092]
  We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark.
  arXiv  Detail & Related papers  (2021-03-09T10:51:24Z)
• Object Removal Attacks on LiDAR-based 3D Object Detectors [6.263478017242508]
  Object Removal Attacks (ORAs) aim to force 3D object detectors to fail. We leverage the default setting of LiDARs that record a single return signal per direction to perturb point clouds in the region of interest. Our results show that the attack is effective in degrading the performance of commonly used 3D object detection models.
  arXiv  Detail & Related papers  (2021-02-07T05:34:14Z)
• Physically Realizable Adversarial Examples for LiDAR Object Detection [72.0017682322147]
  We present a method to generate universal 3D adversarial objects to fool LiDAR detectors. In particular, we demonstrate that placing an adversarial object on the rooftop of any target vehicle to hide the vehicle entirely from LiDAR detectors with a success rate of 80%. This is one step closer towards safer self-driving under unseen conditions from limited training data.
  arXiv  Detail & Related papers  (2020-04-01T16:11:04Z)
• SESS: Self-Ensembling Semi-Supervised 3D Object Detection [138.80825169240302]
  We propose SESS, a self-ensembling semi-supervised 3D object detection framework. Specifically, we design a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data. Our SESS achieves competitive performance compared to the state-of-the-art fully-supervised method by using only 50% labeled data.
  arXiv  Detail & Related papers  (2019-12-26T08:48:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.