BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution

TL;DR

This paper introduces BadRefSR, a backdoor attack method targeting reference-based image super-resolution models, demonstrating how triggers can cause the model to produce attacker-specified outputs without affecting normal performance.

Contribution

The paper presents the first backdoor attack framework specifically designed for reference-based super-resolution models, highlighting a new security vulnerability.

Findings

Backdoor triggers cause models to output attacker-specified images.

The attack remains stealthy on clean inputs, maintaining normal performance.

Extensive experiments validate the effectiveness of BadRefSR.

Abstract

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.