Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gong, Yunpeng, Zeng, Qingyuan, Xu, Dejun, Wang, Zhenzhong, Jiang, Min
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914958054260736
author Gong, Yunpeng
Zeng, Qingyuan
Xu, Dejun
Wang, Zhenzhong
Jiang, Min
author_facet Gong, Yunpeng
Zeng, Qingyuan
Xu, Dejun
Wang, Zhenzhong
Jiang, Min
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17977
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization
Gong, Yunpeng
Zeng, Qingyuan
Xu, Dejun
Wang, Zhenzhong
Jiang, Min
Computer Vision and Pattern Recognition
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.
title Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.17977