Reference-based image super-resolution (RefSR) represents a promising advancement in super-resolution (SR). In contrast to single-image super-resolution (SISR), RefSR leverages an additional reference image to help recover high-frequency details, yet its vulnerability to backdoor attacks has not been explored. To fill this research gap, we propose a novel attack framework called BadRefSR, which embeds backdoors in the RefSR model by adding triggers to the reference images and training with a mixed loss function. Extensive experiments across various backdoor attack settings demonstrate the effectiveness of BadRefSR. The compromised RefSR network performs normally on clean input images, while outputting attacker-specified target images on triggered input images. Our study aims to alert researchers to the potential backdoor risks in RefSR. Codes are available at https://github.com/xuefusiji/BadRefSR.
@article{arxiv.2502.20943,
title = {BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution},
author = {Xue Yang and Tao Chen and Lei Guo and Wenbo Jiang and Ji Guo and Yongming Li and Jiaming He},
journal= {arXiv preprint arXiv:2502.20943},
year = {2025}
}