mlsanityData to 7 Oct 2026

Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios

arXiv 2202.04781 ↗First posted 10 Feb 2022cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Visual detection is a key task in autonomous driving, and it serves as a crucial foundation for self-driving planning and control. Deep neural networks have achieved promising results in various visual tasks, but they are known to be vulnerable to adversarial attacks. A comprehensive understanding of deep visual detectors' vulnerability is required before people can improve their robustness. However, only a few adversarial attack/defense works have focused on object detection, and most of them employed only classification and/or localization losses, ignoring the objectness aspect. In this paper, we identify a serious objectness-related adversarial vulnerability in YOLO detectors and present an effective attack strategy targeting the objectness aspect of visual detection in autonomous vehicles. Furthermore, to address such vulnerability, we propose a new objectness-aware adversarial training approach for visual detection. Experiments show that the proposed attack targeting the objectness aspect is 45.17% and 43.50% more effective than those generated from classification and/or localization losses on the KITTI and COCO traffic datasets, respectively. Also, the proposed adversarial defense approach can improve the detectors' robustness against objectness-oriented attacks by up to 21% and 12% mAP on KITTI and COCO traffic, respectively.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 27 of its 30 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

27 of 30 references.

References · 27

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  12. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
15 more
  1. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  2. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  3. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
  4. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  5. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  6. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  7. 2016Image Captioning with Semantic Attentioncited by 260
  8. 2019Simple Black-box Adversarial Attackscited by 249
  9. 2017On Detecting Adversarial Perturbationscited by 232
  10. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  11. 2016SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Drivingcited by 55
  12. 2019Towards Adversarially Robust Object Detectioncited by 55
  13. 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
  14. 2017Adversarial Examples that Fool Detectorscited by 39
  15. 2018Robust Adversarial Perturbation on Deep Proposal-based Modelscited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 6; 2025: 3; 2026: 3.

20 papers.

Sort:

By area:

  1. 2022CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Modelscited by 8
  2. 2023Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectorscited by 5
  3. 2024Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learningcited by 5
  4. 2024Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detectioncited by 4
  5. 2025AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systemscited by 4
  6. 2022Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Datasetcited by 3
  7. 2023Improving Adversarial Transferability with Scheduled Step Size and Dual Examplecited by 3
  8. 2024Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectorscited by 3
  9. 2024Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devicescited by 3
  10. 2022Efficient Perception, Planning, and Control Algorithm for Vision-Based Automated Vehiclescited by 2
  11. 2023Visual Saliency-Guided Channel Pruning for Deep Visual Detectors in Autonomous Drivingcited by 2
  12. 2023ScAR: Scaling Adversarial Robustness for LiDAR Object Detectioncited by 1
8 more
  1. 2024VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustnesscited by 1
  2. 2024Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectorscited by 1
  3. 2022Enhancing Accuracy and Robustness of Steering Angle Prediction with Attention Mechanismcited by 0
  4. 2025Towards an End-to-End (E2E) Adversarial Learning and Application in the Physical Worldcited by 0
  5. 2025Black-box Adversarial Attacks on CNN-based SLAM Algorithmscited by 0
  6. 2026HyperNet-Adaptation for Diffusion-Based Test Case Generationcited by 0
  7. 2026LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detectioncited by 0
  8. 2026AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Drivingcited by 0