mlsanityData to 14 Oct 2026

Sequence-Preserving Dual-FoV Defense for Traffic Sign and Light Recognition in Autonomous Vehicles

arXiv 2510.02642 ↗First posted 3 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Traffic light and sign recognition are key for Autonomous Vehicles (AVs) because perception mistakes directly influence navigation and safety. In addition to digital adversarial attacks, models are vulnerable to existing perturbations (glare, rain, dirt, or graffiti), which could lead to dangerous misclassifications. The current work lacks consideration of temporal continuity, multistatic field-of-view (FoV) sensing, and robustness to both digital and natural degradation. This study proposes a dual FoV, sequence-preserving robustness framework for traffic lights and signs in the USA based on a multi-source dataset built on aiMotive, Udacity, Waymo, and self-recorded videos from the region of Texas. Mid and long-term sequences of RGB images are temporally aligned for four operational design domains (ODDs): highway, night, rainy, and urban. Over a series of experiments on a real-life application of anomaly detection, this study outlines a unified three-layer defense stack framework that incorporates feature squeezing, defensive distillation, and entropy-based anomaly detection, as well as sequence-wise temporal voting for further enhancement. The evaluation measures included accuracy, attack success rate (ASR), risk-weighted misclassification severity, and confidence stability. Physical transferability was confirmed using probes for recapture. The results showed that the Unified Defense Stack achieved 79.8mAP and reduced the ASR to 18.2%, which is superior to YOLOv8, YOLOv9, and BEVFormer, while reducing the high-risk misclassification to 32%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 150 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

34 of 150 references.

References · 34

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  7. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  8. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  9. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  10. 2016Universal adversarial perturbationscited by 784
  11. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  12. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
22 more
  1. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  2. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  3. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  4. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  5. 2017Countering Adversarial Images using Input Transformationscited by 520
  6. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  7. 2022Diffusion Models for Adversarial Purificationcited by 476
  8. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  9. 2019Simple Black-box Adversarial Attackscited by 251
  10. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  11. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 160
  12. 2017Generative Adversarial Perturbationscited by 153
  13. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 96
  14. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  15. 2019Deep Neural Rejection against Adversarial Examplescited by 32
  16. 2021Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehiclescited by 24
  17. 2019Simple Physical Adversarial Examples against End-to-End Autonomous Driving Modelscited by 17
  18. 2023Dynamic Adversarial Attacks on Autonomous Driving Systemscited by 11
  19. 2021Black-box Adversarial Attacks in Autonomous Vehicle Technologycited by 9
  20. 2024MCTR: Multi Camera Tracking Transformercited by 8
  21. 2024Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspectivecited by 6
  22. 2024Accurate Automatic 3D Annotation of Traffic Lights and Signs for Autonomous Drivingcited by 2

Built on by

Not cited yet.