IRC-SC: Improving Robustness of CNN-based MRI System using SRGAN and CNN
Document Type
Conference Paper
Publication Date
2025
Publication Title
2025 Conference on Artificial Intelligence-CAI-Annual
Abstract
Convolutional Neural Networks (CNNs) have demonstrated remarkable accuracy in automating diagnostic tasks in medical imaging. However, they are highly vulnerable to adversarial attacks, where imperceptible perturbations in input images lead to misclassification. This paper proposes a novel hybrid framework, named IRC-SC combining Super Resolution Generative Adversarial Networks (SRGAN) with CNNs to enhance robustness against adversarial attacks. Using brain MRI datasets, the framework demonstrates over 95% improvement in robustness compared to state-of-the-art methods. It effectively defends against both white-box and black-box attacks, showcasing its potential for secure and reliable diagnostic applications in healthcare.
DOI
10.1109/CAI64502.2025.00095
Recommended Citation
Patel, Gaurang; Chaturvedi,, Vivek; and Kumar, Sathish, "IRC-SC: Improving Robustness of CNN-based MRI System using SRGAN and CNN" (2025). Computer Science Faculty Publications. 15.
https://engagedscholarship.csuohio.edu/encs_facpub/15
Comments
Presented at the 2025 Conference on Artificial Intelligence-CAI-Annual, Santa Clara, CA, MAY 05-07, 2025
This study was supported by the US NSF (Awards DGE 2028397, CNS 2215388); US Department of Energy under Grant DE-SC0024686 and a research grant from IHUB-NTIHAC Foundation, IIT Kanpur (Sanction No. IHUB-NTIHAC/2021/01/9).