mlsanityData to 7 Oct 2026

BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution

arXiv 2502.20943 ↗First posted 28 Feb 2025cs.CV eess.IVcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

25 of 37 references.

References · 25

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  4. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  5. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  6. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  7. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  8. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  9. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  10. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  11. 2019Image Super-Resolution by Neural Texture Transfercited by 119
  12. 2022How to Backdoor Diffusion Models?cited by 102
13 more
  1. 2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 79
  2. 2020Backdoor Attack against Speaker Verificationcited by 62
  3. 2021Dual-Camera Super-Resolution with Aligned Attention Modulescited by 33
  4. 2022Untargeted Backdoor Attack against Object Detectioncited by 28
  5. 2022Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolutioncited by 18
  6. 2021The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Modelscited by 12
  7. 2021Attention-based Multi-Reference Learning for Image Super-Resolutioncited by 12
  8. 2024Stealthy Targeted Backdoor Attacks against Image Captioningcited by 8
  9. 2024Backdoor Attacks against Image-to-Image Networkscited by 7
  10. 2021EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimationcited by 5
  11. 2024Backdoor Attacks against Hybrid Classical-Quantum Neural Networkscited by 5
  12. 2024Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosioncited by 2
  13. 2024Combinational Backdoor Attack against Customized Text-to-Image Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2026State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Spacecited by 9
  2. 2025BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolutioncited by 1
  3. 2026The Double-Edged Sword of Data-Driven Super-Resolution: Adversarial Super-Resolution Modelscited by 1
  4. 2025BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical Worldcited by 0
  5. 2026RefSR-Adv: Adversarial Attack on Reference-based Image Super-Resolution Modelscited by 0
  6. 2026TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoorscited by 0