Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization
This work addresses security vulnerabilities in cross-modal systems, which is important for practical applications using diverse hardware devices, but it appears incremental as it builds on existing adversarial attack research.
The paper tackled the problem of low transferability of adversarial attacks between heterogeneous image modalities like infrared, thermal, and RGB, and proposed a dual-layer gradient-evolutionary optimization framework that improved attack transferability, demonstrating superiority and robustness in extensive testing on multiple datasets.
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.