MEC-Patch：基于本征材料发射率定律的可见-红外跨模态对抗攻击
MEC-Patch: Visible-Infrared Cross-Modal Adversarial Attack Driven by Intrinsic Material Emissivity Laws
浏览论文内容
中文总结 AI 辅助
本文提出基于斯特藩-玻尔兹曼定律的MEC-Patch跨模态对抗攻击框架，结合NSGA-II与DAR策略，可欺骗多模态检测器并提升环境鲁棒性，为多模态感知系统安全评估提供新思路。
中文摘要 AI 辅助
随着可见-红外多模态感知系统在自动驾驶等安全关键领域的广泛部署，评估其跨模态对抗鲁棒性变得愈发重要。然而，现有方法在近似成像本征规律方面存在显著局限：多数研究聚焦单一模态，无法绕过跨模态验证；或简化红外建模为启发式像素强度分布，忽略环境温度波动对对抗稳定性的影响。为填补该空白，本文提出MEC-Patch，一种基于本征物理定律的跨模态对抗攻击框架。利用斯特藩-玻尔兹曼定律，构建基于物理的跨光谱映射，明确关联材料发射率与热辐射。基于该公式，本文揭示：在固定发射率分布下，环境温度变化会引发一致的全局缩放，同时保留发射率诱导的相对对比度。本文利用该特性构建抗温度干扰的对抗扰动，其判别模式在红外模态中保持稳定，从而从根本上降低环境敏感性。此外，采用受物理约束的NSGA-II算法协同优化跨模态有效的基于材料分布的补丁参数，同时通过动态对抗重采样（DAR）策略增强泛化能力。实验结果表明，MEC-Patch可有效欺骗最先进的多模态检测器，在高保真、物理一致及多场景模拟环境中表现出高鲁棒性。本研究为多模态感知系统的安全评估提供了基于物理定律驱动的视角。
英文摘要
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.
