mlsanityData to 14 Oct 2026

Stealthy in Semantics, Antagonistic in Space: Attacking Visible-Infrared Object Detectors via Object-Level Misalignment

arXiv 2609.18133 ↗First posted 16 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Visible-infrared object detectors are used for robust perception under challenging illumination and weather conditions. Current physical attacks apply conspicuous patches to spatially aligned target regions, which are noticeable to human observers. Meanwhile, most of these methods only perturb the appearance within the aligned region, without explicitly targeting the correspondence between modalities or the fusion process. In this paper, we propose CamoShift, an adversarial framework for visible-infrared object detection. By combining visual camouflage with object-level infrared shifting, CamoShift breaks cross-modal spatial alignment and disrupts fusion. Specifically, the Semantic Camouflage Module (SCM) generates a stealthy camouflaged patch that can be attached to the host object and maintains its effectiveness in the infrared branch through an RGB-IR adapter. The Object-level Spatial Decoupling Module (OSDM) shifts the infrared target evidence in a scale-aware manner, so as to break object-level correspondence and disrupt cross-modal fusion. Then, the Harmonic Adversarial loss (HarAdv loss) further balances attack strength and visual stealth during optimization. To the best of our knowledge, we are the first to target both visual stealthiness and attack success in visible-infrared object detection. Extensive experimental results show that CamoShift achieves a superior balance between attack effectiveness and visual stealth. Code and models will be available on GitHub.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 16 Sep 2026.

Builds on

33 of 49 references.

References · 33

  1. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  2. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  3. 2019Object Detection in 20 Years: A Surveycited by 531
  4. 2017Adversarial Patchcited by 517
  5. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 317
  6. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  7. 2021LLVIP: A Visible-infrared Paired Dataset for Low-light Visioncited by 231
  8. 2018Spatially Transformed Adversarial Examplescited by 195
  9. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  10. 2020Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learningcited by 152
  11. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
  12. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
21 more
  1. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  2. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  3. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 93
  4. 2020Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problemscited by 83
  5. 2016Multispectral Deep Neural Networks for Pedestrian Detectioncited by 82
  6. 2023ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detectioncited by 76
  7. 2018Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detectioncited by 74
  8. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  9. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  10. 2023C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detectioncited by 58
  11. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  12. 2022SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagerycited by 47
  13. 2022Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real Worldcited by 42
  14. 2017Learning Cross-Modal Deep Representations for Robust Pedestrian Detectioncited by 34
  15. 2022HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Designcited by 27
  16. 2021Spatio-Contextual Deep Network Based Multimodal Pedestrian Detection For Autonomous Drivingcited by 25
  17. 2023Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical Worldcited by 21
  18. 2024COMO: Cross-Mamba Interaction and Offset-Guided Fusion for Multimodal Object Detectioncited by 18
  19. 2024When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Datasetcited by 10
  20. 2025CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectorscited by 6
  21. 2023Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical worldcited by 4

Built on by

Not cited yet.