Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving

• URL: http://arxiv.org/abs/2101.06784v2
• Date: Tue, 26 Jan 2021 00:40:48 GMT
• Title: Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving
• Authors: James Tu, Huichen Li, Xinchen Yan, Mengye Ren, Yun Chen, Ming Liang, Eilyan Bitar, Ersin Yumer, Raquel Urtasun
• Abstract summary: In this paper, we showcase practical susceptibilities of multi-sensor detection by placing an adversarial object on top of a host vehicle. Our experiments demonstrate that successful attacks are primarily caused by easily corrupted image features. Towards more robust multi-modal perception systems, we show that adversarial training with feature denoising can boost robustness to such attacks significantly.
• Score: 87.3492357041748
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern self-driving perception systems have been shown to improve upon processing complementary inputs such as LiDAR with images. In isolation, 2D images have been found to be extremely vulnerable to adversarial attacks. Yet, there have been limited studies on the adversarial robustness of multi-modal models that fuse LiDAR features with image features. Furthermore, existing works do not consider physically realizable perturbations that are consistent across the input modalities. In this paper, we showcase practical susceptibilities of multi-sensor detection by placing an adversarial object on top of a host vehicle. We focus on physically realizable and input-agnostic attacks as they are feasible to execute in practice, and show that a single universal adversary can hide different host vehicles from state-of-the-art multi-modal detectors. Our experiments demonstrate that successful attacks are primarily caused by easily corrupted image features. Furthermore, we find that in modern sensor fusion methods which project image features into 3D, adversarial attacks can exploit the projection process to generate false positives across distant regions in 3D. Towards more robust multi-modal perception systems, we show that adversarial training with feature denoising can boost robustness to such attacks significantly. However, we find that standard adversarial defenses still struggle to prevent false positives which are also caused by inaccurate associations between 3D LiDAR points and 2D pixels.

Related papers

• TPatch: A Triggered Physical Adversarial Patch [19.768494127237393]
  We propose TPatch, a physical adversarial patch triggered by acoustic signals. To avoid the suspicion of human drivers, we propose a content-based camouflage method and an attack enhancement method to strengthen it.
  arXiv  Detail & Related papers  (2023-12-30T06:06:01Z)
• 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)
• Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World [11.24237636482709]
  We design a unified adversarial patch that can perform cross-modal physical attacks, achieving evasion in both modalities simultaneously with a single patch. We propose a novel boundary-limited shape optimization approach that aims to achieve compact and smooth shapes for the adversarial patch. Our method is evaluated against several state-of-the-art object detectors, achieving an Attack Success Rate (ASR) of over 80%.
  arXiv  Detail & Related papers  (2023-07-27T08:14:22Z)
• Unified Adversarial Patch for Cross-modal Attacks in the Physical World [11.24237636482709]
  We propose a unified adversarial patch to fool visible and infrared object detectors at the same time via a single patch. Considering different imaging mechanisms of visible and infrared sensors, our work focuses on modeling the shapes of adversarial patches. Results show that our unified patch achieves an Attack Success Rate (ASR) of 73.33% and 69.17%, respectively.
  arXiv  Detail & Related papers  (2023-07-15T17:45:17Z)
• 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)
• A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks [84.10546708708554]
  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.
  arXiv  Detail & Related papers  (2022-12-20T13:09:58Z)
• Adversarially-Aware Robust Object Detector [85.10894272034135]
  We propose a Robust Detector (RobustDet) based on adversarially-aware convolution to disentangle gradients for model learning on clean and adversarial images. Our model effectively disentangles gradients and significantly enhances the detection robustness with maintaining the detection ability on clean images.
  arXiv  Detail & Related papers  (2022-07-13T13:59:59Z)
• On the Robustness of Quality Measures for GANs [136.18799984346248]
  This work evaluates the robustness of quality measures of generative models such as Inception Score (IS) and Fr'echet Inception Distance (FID) We show that such metrics can also be manipulated by additive pixel perturbations.
  arXiv  Detail & Related papers  (2022-01-31T06:43:09Z)
• 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)

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.