MEC-Patch: Visible-Infrared Cross-Modal Adversarial Attack Driven by Intrinsic Material Emissivity Laws

2026-08-06

AI Summary

Existing visible-infrared multimodal adversarial attacks struggle to simultaneously achieve cross-modal consistency and physical realism, often exhibiting performance instability under varying environmental temperatures. This work proposes the first cross-modal adversarial attack framework that integrates the physical laws of material emissivity, establishing a physically consistent mapping between visible and infrared images based on the Stefan-Boltzmann law. The approach reveals a key insight: environmental temperature induces only global intensity scaling without altering relative contrast. By combining a physics-constrained NSGA-II multi-objective optimization with a dynamic adversarial resampling strategy, the method significantly enhances attack success rates against state-of-the-art multimodal detectors in high-fidelity simulated environments, while demonstrating strong temperature robustness and physical interpretability.

Abstract

With the widespread deployment of visible-infrared multimodal perception systems in safety-critical domains such as autonomous driving, evaluating their cross-modal adversarial robustness has become increasingly vital. However, existing approaches exhibit significant limitations in approximating the intrinsic laws of imaging. Most studies either focus on a single modality, failing to bypass cross-modal verification, or simplify infrared modeling into heuristic pixel-intensity distributions, neglecting the impact of ambient temperature fluctuations on adversarial stability. To bridge this gap, this paper proposes MEC-Patch, a cross-modal adversarial attack framework driven by intrinsic physical laws. By leveraging the Stefan-Boltzmann Law, we establish a physics-grounded cross-spectral mapping that explicitly links material emissivity to thermal radiation. Building on this formulation, we reveal that, under a fixed emissivity distribution, ambient temperature variations induce consistent global scaling while preserving relative emissivity-induced contrast. We exploit this property to construct temperature-robust adversarial perturbations whose discriminative patterns remain stable in the infrared modality, thereby fundamentally mitigating environmental sensitivity. Furthermore, we employ the physics-constrained NSGA-II algorithm to synergistically optimize the material-distribution-based patch parameters effective across both modalities, while enhancing generalization through a Dynamic Adversarial Resampling (DAR) strategy. Experimental results demonstrate that MEC-Patch effectively deceives state-of-the-art multimodal detectors and exhibits high robustness within high-fidelity, physically-consistent, and multi-scene simulation environments. This research provides a physical-law-driven perspective for the security assessment of multimodal perception systems.

Problem

• cross-modal adversarial attack
• visible-infrared perception
• material emissivity
• ambient temperature variation
• physical consistency

Innovation

• cross-modal adversarial attack
• material emissivity
• Stefan-Boltzmann Law
• temperature-robust perturbation
• physics-constrained optimization