Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling

• URL: http://arxiv.org/abs/2608.30839v1
• Date: Mon, 31 Aug 2026 14:09:41 GMT
• Title: Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling
• Abstract summary: We propose infrared adversarial clothing designed to evade thermal person detectors in real-world scenarios.<n>The design is based on 3D modeling, which makes it easier to simulate multiangle scenes near the real world compared to 2D modeling.<n>In physical attacks, we achieved an attack success rate of 80.11% indoors and 76.85% outdoors against YOLOv9.
• Score: 44.67395163268884
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Thermal Infrared detection is widely used in autonomous driving, medical AI, etc., but its security has only attracted attention recently. We propose infrared adversarial clothing designed to evade thermal person detectors in real-world scenarios. The design of the adversarial clothing is based on 3D modeling, which makes it easier to simulate multiangle scenes near the real world compared to 2D modeling. We optimized the black patch layout pattern of 3D clothing based on the adversarial example technique and made physical adversarial clothing using the aerogel. The idea is to paste a set of square aerogel patches, which display black squares in thermal images, in the inner side of clothing at specific locations with specific orientations. To enhance realism, we propose a method to build infrared 3D models with real infrared photos and develop texture maps for 3D models to simulate varied infrared characteristics over time and location. In physical attacks, we achieved an attack success rate of 80.11\% indoors and 76.85\% outdoors against YOLOv9. In contrast, randomly placed patches yielded much lower success rates (26.53\% indoors and 23.03\% outdoors). The adversarial clothing also showed good transferability to unknown detectors with an ensemble attack method, demonstrating the effectiveness of our approach.

Related papers

• Infrared Adversarial Car Stickers [18.913361704019973]
  We propose a physical attack method against infrared detectors based on 3D modeling, which is applied to a real car. The goal is to design a set of infrared adversarial stickers to make cars invisible to infrared detectors at various viewing angles, distances, and scenes.
  arXiv  Detail & Related papers  (2024-05-16T09:26:19Z)
• PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations [62.14943588289551]
  We introduce PhysAvatar, a novel framework that combines inverse rendering with inverse physics to automatically estimate the shape and appearance of a human. PhysAvatar reconstructs avatars dressed in loose-fitting clothes under motions and lighting conditions not seen in the training data.
  arXiv  Detail & Related papers  (2024-04-05T21:44:57Z)
• 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)
• Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling [19.575338491567813]
  We craft adversarial texture for clothes based on 3D modeling. We propose adversarial camouflage textures (AdvCaT) that resemble one kind of the typical textures of daily clothes. We printed the developed 3D texture pieces on fabric materials and tailored them into T-shirts and trousers.
  arXiv  Detail & Related papers  (2023-07-04T15:31:03Z)
• Physically Adversarial Infrared Patches with Learnable Shapes and Locations [1.1172382217477126]
  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.
  arXiv  Detail & Related papers  (2023-03-24T09:11:36Z)
• 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)
• Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real World [28.61452368555484]
  We proposed the infrared adversarial clothing, which could fool infrared pedestrian detectors at different angles. The core of our method is to design a basic pattern that can be expanded periodically. We used the model ensemble technique to improve the attack transferability to unseen models.
  arXiv  Detail & Related papers  (2022-05-12T07:02:34Z)
• Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors [72.7633556669675]
  This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes. Unlike existing adversarial patches, our new 3D adversarial patch is shown to fool state-of-the-art deep object detectors robustly under varying views.
  arXiv  Detail & Related papers  (2021-04-22T14:36:08Z)
• High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation [117.32310997522394]
  3D video avatars can empower virtual communications by providing compression, privacy, entertainment, and a sense of presence in AR/VR. Existing person-specific 3D models are not robust to lighting, hence their results typically miss subtle facial behaviors and cause artifacts in the avatar. This paper addresses previous limitations by learning a deep learning lighting model, that in combination with a high-quality 3D face tracking algorithm, provides a method for subtle and robust facial motion transfer from a regular video to a 3D photo-realistic avatar.
  arXiv  Detail & Related papers  (2021-03-29T18:33:49Z)
• Learning to Transfer Texture from Clothing Images to 3D Humans [50.838970996234465]
  We present a method to automatically transfer textures of clothing images to 3D garments worn on top SMPL, in real time. We first compute training pairs of images with aligned 3D garments using a custom non-rigid 3D to 2D registration method, which is accurate but slow. Our model opens the door to applications such as virtual try-on, and allows for generation of 3D humans with varied textures which is necessary for learning.
  arXiv  Detail & Related papers  (2020-03-04T12:53:58Z)

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.