mlsanityData to 14 Oct 2026

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World

arXiv 2404.19417 ↗First posted 30 Apr 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Backdoor attacks have been well-studied in visible light object detection (VLOD) in recent years. However, VLOD can not effectively work in dark and temperature-sensitive scenarios. Instead, thermal infrared object detection (TIOD) is the most accessible and practical in such environments. In this paper, our team is the first to investigate the security vulnerabilities associated with TIOD in the context of backdoor attacks, spanning both the digital and physical realms. We introduce two novel types of backdoor attacks on TIOD, each offering unique capabilities: Object-affecting Attack and Range-affecting Attack. We conduct a comprehensive analysis of key factors influencing trigger design, which include temperature, size, material, and concealment. These factors, especially temperature, significantly impact the efficacy of backdoor attacks on TIOD. A thorough understanding of these factors will serve as a foundation for designing physical triggers and temperature controlling experiments. Our study includes extensive experiments conducted in both digital and physical environments. In the digital realm, we evaluate our approach using benchmark datasets for TIOD, achieving an Attack Success Rate (ASR) of up to 98.21%. In the physical realm, we test our approach in two real-world settings: a traffic intersection and a parking lot, using a thermal infrared camera. Here, we attain an ASR of up to 98.38%.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

19 of 35 references.

References · 19

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  3. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  4. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
  5. 2020Backdoor Learning: A Surveycited by 426
  6. 2019Hidden Trigger Backdoor Attackscited by 371
  7. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  8. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  9. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  10. 2014Multiple Object Tracking: A Literature Reviewcited by 166
  11. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 118
  12. 2020Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxificationcited by 95
7 more
  1. 2021Backdoor Attack in the Physical Worldcited by 84
  2. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  3. 2022Few-Shot Backdoor Attacks on Visual Object Trackingcited by 35
  4. 2022Membership Inference via Backdooringcited by 27
  5. 2021Robust Backdoor Attacks against Deep Neural Networks in Real Physical Worldcited by 20
  6. 2021DoubleStar: Long-Range Attack Towards Depth Estimation based Obstacle Avoidance in Autonomous Systemscited by 10
  7. 2022Backdoor Attacks on Crowd Countingcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 2.

6 papers.

  1. 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Modelscited by 17
  2. 2025Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Modelscited by 7
  3. 2025FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognitioncited by 1
  4. 2024Twin Trigger Generative Networks for Backdoor Attacks against Object Detectioncited by 0
  5. 2026Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Trainingcited by 0
  6. 2026Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MOBA: A Material-Oriented Backdoor Attack against LiDAR-based 3D Object Detection Systems
  2. 2022Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World
  3. 2026DETOUR: A Practical Backdoor Attack against Object Detection ↗
  4. 2024On the Credibility of Backdoor Attacks Against Object Detectors in the Physical World
  5. 2025Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World
  6. 2024Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
  7. 2023Robust Backdoor Attacks on Object Detection in Real World
  8. 2024Mask-based Invisible Backdoor Attacks on Object Detection