Endmember Extraction Guided Transferable Adversarial Attack for Hyperspectral Image Classification

Authors:
Publisher website
Google Scholar
Abstract
In recent years, adversarial attacks in hyperspectral image (HSI) classification have attracted increasing attention. However, most existing approaches rely on the loss or gradient information of a single classifier to optimize pixel-level adversarial perturbations, which undermines the reflectance consistency of hyperspectral data and limits the transferability of adversarial examples across different classifier architectures. These drawbacks compromise both the physical interpretability and the practical applicability of adversarial examples. To address these challenges, this paper proposes an endmember extraction guided transferable adversarial attack (EEGTAA) framework for generating adversarial examples that preserve reflectance consistency while achieving strong transferability. Specifically, EEGTAA first employs endmember extraction techniques to obtain the endmember composition of HSIs and introduces adversarial perturbations into the endmember matrix, thereby ensuring the physical plausibility of the generated samples. Subsequently, EEGTAA integrates the loss gradients from multiple heterogeneous classifiers to optimize perturbations on the endmember matrix, enhancing the threat to target classifiers with unknown architectures and parameters. Furthermore, a conflict-mitigation gradient optimization strategy is theoretically derived, which utilizes weighted loss gradients to corrects the perturbation update direction within the hyperspherical neighborhood of the averaged gradient, alleviating the suboptimal optimization caused by divergent gradient directions across classifiers. Experimental results on benchmark HSI datasets demonstrate that EEGTAA not only produces adversarial examples with high attack performance and reflectance consistency but also exhibits superior transferability across classifier architectures.
Funding Information
  • National Natural Science Foundation of China (62576259)
  • Innovation Capability Support Plan of Shaanxi Province (2023KJXX-144)
  • Fundamental Research Funds for the Central Universities

This publication has 63 references indexed in Scilit: