RefSR-Adv: Adversarial Attack on Reference-based Image Super-Resolution Models

TL;DR

This paper introduces RefSR-Adv, an adversarial attack method that degrades reference-based super-resolution models by perturbing reference images, exposing a security vulnerability and emphasizing the need for robustness in such systems.

Contribution

The paper presents the first adversarial attack specifically targeting reference-based super-resolution models, demonstrating their vulnerability and analyzing the impact of reference similarity on attack effectiveness.

Findings

RefSR-Adv significantly degrades SR output quality.

Attack effectiveness correlates with reference-image similarity.

Vulnerability observed across CNN, Transformer, and Mamba architectures.

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.