Abstract
Single Image Super-Resolution (SISR) aims to recover high-resolution images from low-resolution inputs. Unlike SISR, Reference-based Super-Resolution (RefSR) leverages an additional high-resolution reference image to facilitate the recovery of high-frequency textures. However, existing research mainly focuses on backdoor attacks targeting RefSR, while the vulnerability of the adversarial attacks targeting RefSR has not been fully explored. To fill this research gap, we propose RefSR-Adv, an adversarial attack that degrades SR outputs by perturbing only the reference image. By maximizing the difference between adversarial and clean outputs, RefSR-Adv induces significant performance degradation and generates severe artifacts across CNN, Transformer, and Mamba architectures on the CUFED5, WR-SR, and DRefSR datasets. Importantly, experiments confirm a positive correlation between the similarity of the low-resolution input and the reference image and attack effectiveness, revealing that the model's over-reliance on reference features is a key security flaw. This study reveals a security vulnerability in RefSR systems, aiming to urge researchers to pay attention to the robustness of RefSR.
Abstract (translated)
单图像超分辨率（SISR）的目标是从低分辨率的输入中恢复出高分辨率的图像。不同于SISR，基于参考的超分辨率（RefSR）利用了一张额外的高分辨率参考图像来帮助恢复高频纹理信息。然而，现有的研究主要集中在针对RefSR的后门攻击上，而关于对抗性攻击对RefSR系统脆弱性的探索尚未充分进行。为了填补这一研究空白，我们提出了一种名为RefSR-Adv的对抗性攻击方法，该方法通过仅扰动参考图像来降低超分辨率输出的质量。通过最大化对抗样本和干净输入之间的差异，RefSR-Adv在CUFED5、WR-SR 和 DRefSR 数据集上针对卷积神经网络（CNN）、Transformer 和 Mamba 架构的模型导致了显著性能下降，并生成了严重的伪影。 尤为重要的是，实验结果证实了低分辨率输入与参考图像之间的相似度和攻击效果之间存在正相关关系。这一发现揭示出，过度依赖参考特征是模型的一个关键安全漏洞。本研究揭示了RefSR系统中的一种安全性脆弱性，并旨在提醒研究人员注意RefSR的鲁棒性问题。
URL
https://arxiv.org/abs/2601.01202
