Back to articles
Proceedings Paper
Volume: 38 | Article ID: COIMG-120
Image
The Double-edged Sword of Data-driven Super-Resolution: Adversarial Super-resolution Models
  DOI :  10.2352/EI.2026.38.15.COIMG-120  Published OnlineMarch 2026
Abstract
Abstract

Data-driven super-resolution (SR) methods are often integrated into imaging pipelines as preprocessing steps to improve downstream tasks such as classification and detection. However, these SR models introduce a previously unexplored attack surface into imaging pipelines. In this paper, we present AdvSR, a framework demonstrating that adversarial behavior can be embedded directly into SR model weights during training, requiring no access to inputs at inference time. Unlike prior attacks that perturb inputs or rely on backdoor triggers, AdvSR operates entirely at the model level. By jointly optimizing for reconstruction quality and targeted adversarial outcomes, AdvSR produces models that appear benign under standard image quality metrics while inducing downstream misclassification. We evaluate AdvSR on three SR architectures (SRCNN, EDSR, SwinIR) paired with a YOLOv11 classifier and demonstrate that AdvSR models can achieve high attack success rates with minimal quality degradation. These findings highlight a new model-level threat for imaging pipelines, with implications for how practitioners source and validate models in safety-critical applications.

Subject Areas :
Views 31
Downloads 14
 articleview.views 31
 articleview.downloads 14
  Cite this article 

Haley Duba-Sullivan, Steven R. Young, Emma J. Reid, "The Double-edged Sword of Data-driven Super-Resolution: Adversarial Super-resolution Modelsin Electronic Imaging,  2026,  pp 120-1 - 120-7,  https://doi.org/10.2352/EI.2026.38.15.COIMG-120

 Copy citation
  Copyright statement 
Copyright ©2026 Society for Imaging Science and Technology 2026
ei
Electronic Imaging
2470-1173
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA