$\textrm{A}^{\textrm{2}}$RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion
This addresses robustness in image fusion for applications like surveillance, but it is incremental as it builds on existing fusion methods with adversarial training.
The paper tackles the problem of adversarial attacks on infrared and visible image fusion models by proposing A²RNet, which uses an adversarial training paradigm and a transformer-based module to maintain high-fidelity fusion results and downstream task performance under attacks.
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.