Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling

2026-03-26

AI Summary

This work addresses the vulnerability of infrared object detection to disturbances and adversarial attacks in complex environments, a limitation exacerbated by existing data-driven methods that overlook the physical properties of infrared imagery. To enhance robustness, the study introduces, for the first time, the inter-class grayscale ordering induced by thermal radiation as a physical prior. This prior is formalized into a stability metric and integrated into an adversarial training framework, enabling a deep fusion of physical laws with deep learning. Through thermal radiation modeling, quantification of grayscale order, and knowledge-guided adversarial training, the proposed method significantly improves clean-sample accuracy across three infrared datasets and six mainstream detection models, while simultaneously enhancing robustness and semantic consistency against both adversarial attacks and common perturbations.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Search and Optimization: Adversarial Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In complex environments, infrared object detection exhibits broad applicability and stability across diverse scenarios. However, infrared object detection is vulnerable to both common corruptions and adversarial examples, leading to potential security risks. To improve the robustness of infrared object detection, current methods mostly adopt a data-driven ideology, which only superficially drives the network to fit the training data without specifically considering the unique characteristics of infrared images, resulting in limited robustness. In this paper, we revisit infrared physical knowledge and find that relative thermal radiation relations between different classes can be regarded as a reliable knowledge source under the complex scenarios of adversarial examples and common corruptions. Thus, we theoretically model thermal radiation relations based on the rank order of gray values for different classes, and further quantify the stability of various inter-class thermal radiation relations. Based on the above theoretical framework, we propose Knowledge-Guided Adversarial Training (KGAT) for infrared object detection, in which infrared physical knowledge is embedded into the adversarial training process, and the predicted results are optimized to be consistent with the actual physical laws. Extensive experiments on three infrared datasets and six mainstream infrared object detection models demonstrate that KGAT effectively enhances both clean accuracy and robustness against adversarial attacks and common corruptions.

Problem

• infrared object detection
• adversarial examples
• common corruptions
• robustness
• thermal radiation

Innovation

• Knowledge-Guided Adversarial Training
• Thermal Radiation Modeling
• Infrared Object Detection
• Physical Prior Knowledge
• Robustness Enhancement