Physically Adversarial Infrared Patches with Learnable Shapes and Locations

• URL: http://arxiv.org/abs/2303.13868v1
• Date: Fri, 24 Mar 2023 09:11:36 GMT
• Title: Physically Adversarial Infrared Patches with Learnable Shapes and Locations
• Authors: Wei Xingxing and Yu Jie and Huang Yao
• Abstract summary: We propose a physically feasible infrared attack method called "adversarial infrared patches" Considering the imaging mechanism of infrared cameras by capturing objects' thermal radiation, adversarial infrared patches conduct attacks by attaching a patch of thermal insulation materials on the target object to manipulate its thermal distribution. We verify adversarial infrared patches in different object detection tasks with various object detectors.
• Score: 1.1172382217477126
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Owing to the extensive application of infrared object detectors in the safety-critical tasks, it is necessary to evaluate their robustness against adversarial examples in the real world. However, current few physical infrared attacks are complicated to implement in practical application because of their complex transformation from digital world to physical world. To address this issue, in this paper, we propose a physically feasible infrared attack method called "adversarial infrared patches". Considering the imaging mechanism of infrared cameras by capturing objects' thermal radiation, adversarial infrared patches conduct attacks by attaching a patch of thermal insulation materials on the target object to manipulate its thermal distribution. To enhance adversarial attacks, we present a novel aggregation regularization to guide the simultaneous learning for the patch' shape and location on the target object. Thus, a simple gradient-based optimization can be adapted to solve for them. We verify adversarial infrared patches in different object detection tasks with various object detectors. Experimental results show that our method achieves more than 90\% Attack Success Rate (ASR) versus the pedestrian detector and vehicle detector in the physical environment, where the objects are captured in different angles, distances, postures, and scenes. More importantly, adversarial infrared patch is easy to implement, and it only needs 0.5 hours to be constructed in the physical world, which verifies its effectiveness and efficiency.

Related papers

• Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World [47.76657100827679]
  We introduce two novel types of backdoor attacks on thermal infrared object detection (TIOD) Key factors influencing trigger design include temperature, size, material, and concealment. In the digital realm, we evaluate our approach using benchmark datasets for TIOD, achieving an Attack Success Rate (ASR) of up to 98.21%.
  arXiv  Detail & Related papers  (2024-04-30T10:03:26Z)
• Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors [0.0]
  We propose a novel infrared physical attack termed Adrial Infrared Geometry (textversabfAdvIG) In digital attack experiments, line, triangle, and ellipse patterns achieve attack success rates of 93.1%, 86.8%, and 100.0%, respectively. On average, the line, triangle, and ellipse achieve attack success rates of 61.1%, 61.2%, and 96.2%, respectively.
  arXiv  Detail & Related papers  (2024-03-06T12:55:21Z)
• Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World [0.0]
  Existing approaches, like white-box infrared attacks using bulb boards and QR suits, lack realism and stealthiness. We propose Adversarial Infrared Curves (AdvIC) to bridge these gaps. Our experiments confirm AdvIC's effectiveness, achieving 94.8% and 67.2% attack success rates for digital and physical attacks, respectively.
  arXiv  Detail & Related papers  (2023-12-21T12:21:57Z)
• 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)
• Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical World [4.504479592538401]
  We propose a novel physical attack called adversarial infrared blocks (AdvIB) By optimizing the physical parameters of the adversarial infrared blocks, this method can execute a stealthy black-box attack on thermal imaging system from various angles. For stealthiness, our method involves attaching the adversarial infrared block to the inside of clothing, enhancing its stealthiness.
  arXiv  Detail & Related papers  (2023-04-21T02:53:56Z)
• HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design [60.97064635095259]
  textscHotCold Block is a novel physical attack for infrared detectors that hide persons utilizing the wearable Warming Paste and Cooling Paste. By attaching these readily available temperature-controlled materials to the body, textscHotCold Block evades human eyes efficiently.
  arXiv  Detail & Related papers  (2022-12-12T05:23:11Z)
• 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)
• Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning [64.92447072894055]
  Infrared (IR) cameras are robust under adverse illumination and lighting conditions. We propose an algorithm meta-learning framework to improve existing UDA methods. We produce a state-of-the-art thermal detector for the KAIST and DSIAC datasets.
  arXiv  Detail & Related papers  (2021-10-07T02:28:18Z)
• Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds [155.388487263872]
  We propose a new infrared small-dim target detection method with the transformer. We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range. We also design a feature enhancement module to learn more features of small-dim targets.
  arXiv  Detail & Related papers  (2021-09-29T12:23:41Z)
• Exploring Thermal Images for Object Detection in Underexposure Regions for Autonomous Driving [67.69430435482127]
  Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack in capturing interpretable signals. This work proposes a domain adaptation framework which employs a style transfer technique for transfer learning from visible spectrum images to thermal images.
  arXiv  Detail & Related papers  (2020-06-01T09:59:09Z)

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.