Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors

• URL: http://arxiv.org/abs/2506.04823v1
• Date: Thu, 05 Jun 2025 09:41:12 GMT
• Title: Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors
• Authors: Svetlana Pavlitska, Jamie Robb, Nikolai Polley, Melih Yazgan, J. Marius Zöllner,
• Abstract summary: This work shows how CNNs for traffic light detection can be attacked with printed patches.<n>We propose a threat model, where each instance of a traffic light is attacked with a patch placed under it, and describe a training strategy.<n>Our experiments show realistic targeted red-to-green label-flipping attacks and attacks on pictogram classification.
• Score: 10.525130568825572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Realistic adversarial attacks on various camera-based perception tasks of autonomous vehicles have been successfully demonstrated so far. However, only a few works considered attacks on traffic light detectors. This work shows how CNNs for traffic light detection can be attacked with printed patches. We propose a threat model, where each instance of a traffic light is attacked with a patch placed under it, and describe a training strategy. We demonstrate successful adversarial patch attacks in universal settings. Our experiments show realistic targeted red-to-green label-flipping attacks and attacks on pictogram classification. Finally, we perform a real-world evaluation with printed patches and demonstrate attacks in the lab settings with a mobile traffic light for construction sites and in a test area with stationary traffic lights. Our code is available at https://github.com/KASTEL-MobilityLab/attacks-on-traffic-light-detection.

Related papers

• Transient Adversarial 3D Projection Attacks on Object Detection in Autonomous Driving [15.516055760190884]
  We introduce an adversarial 3D projection attack specifically targeting object detection in autonomous driving scenarios. Our results demonstrate the effectiveness of the proposed attack in deceiving YOLOv3 and Mask R-CNN in physical settings.
  arXiv  Detail & Related papers  (2024-09-25T22:27:11Z)
• Invisible Optical Adversarial Stripes on Traffic Sign against Autonomous Vehicles [10.17957244747775]
  This paper presents an attack that uses light-emitting diodes and exploits the camera's rolling shutter effect to mislead traffic sign recognition. The attack is stealthy because the stripes on the traffic sign are invisible to human. We discuss the countermeasures at the levels of camera sensor, perception model, and autonomous driving system.
  arXiv  Detail & Related papers  (2024-07-10T09:55:31Z)
• Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perception [25.566091959509986]
  Road signs indicate locally active rules, such as speed limits and requirements to yield or stop. Recent research has demonstrated attacks, such as adding stickers or projected colored patches to signs, that cause CAV misinterpretation. We have developed an effective physical-world attack that leverages the sensitivity of filterless image sensors.
  arXiv  Detail & Related papers  (2024-01-07T21:22:42Z)
• 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)
• Object-fabrication Targeted Attack for Object Detection [54.10697546734503]
  adversarial attack for object detection contains targeted attack and untargeted attack. New object-fabrication targeted attack mode can mislead detectors tofabricate extra false objects with specific target labels.
  arXiv  Detail & Related papers  (2022-12-13T08:42:39Z)
• REAP: A Large-Scale Realistic Adversarial Patch Benchmark [14.957616218042594]
  Adrial patch attacks present a critical threat to cyber-physical systems that rely on cameras such as autonomous cars. We propose the REAP benchmark, a digital benchmark that allows the user to evaluate patch attacks on real images. Built on top of the Mapillary Vistas dataset, our benchmark contains over 14,000 traffic signs.
  arXiv  Detail & Related papers  (2022-12-12T03:35:05Z)
• Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks [76.35478518372692]
  We introduce epsilon-illusory, a novel form of adversarial attack on sequential decision-makers. Compared to existing attacks, we empirically find epsilon-illusory to be significantly harder to detect with automated methods. Our findings suggest the need for better anomaly detectors, as well as effective hardware- and system-level defenses.
  arXiv  Detail & Related papers  (2022-07-20T19:49:09Z)
• Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon [79.33449311057088]
  We study a new type of optical adversarial examples, in which the perturbations are generated by a very common natural phenomenon, shadow. We extensively evaluate the effectiveness of this new attack on both simulated and real-world environments.
  arXiv  Detail & Related papers  (2022-03-08T02:40:18Z)
• Automating Privilege Escalation with Deep Reinforcement Learning [71.87228372303453]
  In this work, we exemplify the potential threat of malicious actors using deep reinforcement learning to train automated agents. We present an agent that uses a state-of-the-art reinforcement learning algorithm to perform local privilege escalation. Our agent is usable for generating realistic attack sensor data for training and evaluating intrusion detection systems.
  arXiv  Detail & Related papers  (2021-10-04T12:20:46Z)
• Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks [62.87459235819762]
  In a real-world scenario like autonomous driving, more attention should be devoted to real-world adversarial examples (RWAEs) This paper presents an in-depth evaluation of the robustness of popular SS models by testing the effects of both digital and real-world adversarial patches.
  arXiv  Detail & Related papers  (2021-08-13T11:49:09Z)
• Dynamic Adversarial Patch for Evading Object Detection Models [47.32228513808444]
  We present an innovative attack method against object detectors applied in a real-world setup. Our method uses dynamic adversarial patches which are placed at multiple predetermined locations on a target object. We improved the attack by generating patches that consider the semantic distance between the target object and its classification.
  arXiv  Detail & Related papers  (2020-10-25T08:55:40Z)

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.