In recent years, despite significant advancements in adversarial attack research, the security challenges in cross-modal scenarios, such as the transferability of adversarial attacks between infrared, thermal, and RGB images, have been overlooked. These heterogeneous image modalities collected by different hardware devices are widely prevalent in practical applications, and the substantial differences between modalities pose significant challenges to attack transferability. In this work, we explore a novel cross-modal adversarial attack strategy, termed multiform attack. We propose a dual-layer optimization framework based on gradient-evolution, facilitating efficient perturbation transfer between modalities. In the first layer of optimization, the framework utilizes image gradients to learn universal perturbations within each modality and employs evolutionary algorithms to search for shared perturbations with transferability across different modalities through secondary optimization. Through extensive testing on multiple heterogeneous datasets, we demonstrate the superiority and robustness of Multiform Attack compared to existing techniques. This work not only enhances the transferability of cross-modal adversarial attacks but also provides a new perspective for understanding security vulnerabilities in cross-modal systems.

翻译：近年来，尽管对抗攻击研究取得了显著进展，但跨模态场景中的安全性挑战——例如红外、热成像与RGB图像之间对抗攻击的迁移性——却一直被忽视。这些由不同硬件设备采集的异构图像模态在实际应用中广泛存在，模态间的显著差异给攻击迁移性带来了巨大挑战。本研究探索了一种新颖的跨模态对抗攻击策略，称为多形式攻击。我们提出了一个基于梯度-进化的双层优化框架，以促进模态间扰动的高效迁移。在优化第一层中，该框架利用图像梯度学习各模态内的通用扰动，并通过进化算法在第二层优化中搜索具有跨模态迁移性的共享扰动。通过在多个异构数据集上的广泛测试，我们证明了多形式攻击相较于现有技术的优越性与鲁棒性。这项工作不仅提升了跨模态对抗攻击的迁移性，也为理解跨模态系统的安全漏洞提供了新的视角。