mlsanityData to 14 Oct 2026

The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition

arXiv 2409.12394 ↗First posted 19 Sep 2024cs.CV cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Recently, traffic sign recognition (TSR) systems have become a prominent target for physical adversarial attacks. These attacks typically rely on conspicuous stickers and projections, or using invisible light and acoustic signals that can be easily blocked. In this paper, we introduce a novel attack medium, i.e., fluorescent ink, to design a stealthy and effective physical adversarial patch, namely FIPatch, to advance the state-of-the-art. Specifically, we first model the fluorescence effect in the digital domain to identify the optimal attack settings, which guide the real-world fluorescence parameters. By applying a carefully designed fluorescence perturbation to the target sign, the attacker can later trigger a fluorescent effect using invisible ultraviolet light, causing the TSR system to misclassify the sign and potentially leading to traffic accidents. We conducted a comprehensive evaluation to investigate the effectiveness of FIPatch, which shows a success rate of 98.31% in low-light conditions. Furthermore, our attack successfully bypasses five popular defenses and achieves a success rate of 96.72%.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 40 of its 61 references that are in the map. First posted on arXiv 19 Sep 2024.

Builds on

40 of 61 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Mask R-CNNcited by 7,277
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  12. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
28 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,659
  2. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  3. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  4. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  5. 2017One pixel attack for fooling deep neural networkscited by 582
  6. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  7. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  8. 2018Physical Adversarial Examples for Object Detectorscited by 163
  9. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  10. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  11. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 105
  12. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 93
  13. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  14. 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 70
  15. 2020The Translucent Patch: A Physical and Universal Attack on Object Detectorscited by 62
  16. 2020Understanding Adversarial Examples from the Mutual Influence of Images and Perturbationscited by 59
  17. 2020SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbationscited by 50
  18. 2016HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detectioncited by 46
  19. 2020Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effectcited by 40
  20. 2023Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attackcited by 37
  21. 2022Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systemscited by 27
  22. 2023TPatch: A Triggered Physical Adversarial Patchcited by 22
  23. 2022Rolling Colors: Adversarial Laser Exploits against Traffic Light Recognitioncited by 15
  24. 2024Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perceptioncited by 14
  25. 2018Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attackscited by 13
  26. 2022Adversarial Color Film: Effective Physical-World Attack to DNNscited by 11
  27. 2020Targeted Physical-World Attention Attack on Deep Learning Models in Road Sign Recognitioncited by 7
  28. 2021SoundFence: Securing Ultrasonic Sensors in Vehicles Using Physical-Layer Defensecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025A Contemporary Survey of Large Language Model Assisted Program Analysiscited by 11
  2. 2025DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protectioncited by 0
  3. 2026Hiding in Plain Sight: An Effective Physical Adversarial Patch Attack against Visual-Infrared Fused Face Detectioncited by 0