$\textrm{A}^{\textrm{2}}$RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion

TL;DR

This paper introduces A2RNet, a novel neural network designed to improve the robustness of infrared and visible image fusion against adversarial attacks, ensuring high-quality fused images and reliable downstream task performance.

Contribution

The paper proposes a new adversarial attack resilient network with an anti-attack loss and a transformer-based refinement module for robust image fusion.

Findings

A2RNet effectively mitigates adversarial perturbations.

Fused image quality remains high under attack.

Downstream task performance is preserved under adversarial conditions.

Abstract

Infrared and visible image fusion (IVIF) is a crucial technique for enhancing visual performance by integrating unique information from different modalities into one fused image. Exiting methods pay more attention to conducting fusion with undisturbed data, while overlooking the impact of deliberate interference on the effectiveness of fusion results. To investigate the robustness of fusion models, in this paper, we propose a novel adversarial attack resilient network, called $\textrm{A}^{\textrm{2}}$RNet. Specifically, we develop an adversarial paradigm with an anti-attack loss function to implement adversarial attacks and training. It is constructed based on the intrinsic nature of IVIF and provide a robust foundation for future research advancements. We adopt a Unet as the pipeline with a transformer-based defensive refinement module (DRM) under this paradigm, which guarantees fused image quality in a robust coarse-to-fine manner. Compared to previous works, our method mitigates the adverse effects of adversarial perturbations, consistently maintaining high-fidelity fusion results. Furthermore, the performance of downstream tasks can also be well maintained under adversarial attacks. Code is available at https://github.com/lok-18/A2RNet.