Towards practical and privacy-preserving CNN inference service for cloud-based medical imaging analysis: A homomorphic encryption-based approach

• Published in: Computer methods and programs in biomedicine Vol. 261; p. 108599
• Main Authors: Bai, Yanan, Zhao, Hongbo, Shi, Xiaoyu, Chen, Lin
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.04.2025
• Subjects: Algorithms; Cloud Computing; Computer Security; Confidentiality; Convolutional neural network; Deep Learning; Diagnostic Imaging; Homomorphic encryption; Humans; Image Processing, Computer-Assisted - methods; Machine learning; Medical imaging analysis; Neural Networks, Computer; Privacy; Privacy computing; Cloud computing; Privacy computing; Homomorphic encryption; Convolutional neural network; Machine learning; Medical imaging analysis
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2025.108599

Cloud-based Deep Learning as a Service (DLaaS) has transformed biomedicine by enabling healthcare systems to harness the power of deep learning for biomedical data analysis. However, privacy concerns emerge when sensitive user data must be transmitted to untrusted cloud servers. Existing privacy-preserving solutions are hindered by significant latency issues, stemming from the computational complexity of inner product operations in convolutional layers and the high communication costs of evaluating nonlinear activation functions. These limitations make current solutions impractical for real-world applications. In this paper, we address the challenges in mobile cloud-based medical imaging analysis, where users aim to classify private body-related radiological images using a Convolutional Neural Network (CNN) model hosted on a cloud server while ensuring data privacy for both parties. We propose PPCNN, a practical and privacy-preserving framework for CNN Inference. It introduces a novel mixed protocol that combines a low-expansion homomorphic encryption scheme with the noise-based masking method. Our framework is designed based on three key ideas: (1) optimizing computation costs by shifting unnecessary and expensive homomorphic multiplication operations to the offline phase, (2) introducing a coefficient-aware packing method to enable efficient homomorphic operations during the linear layer of the CNN, and (3) employing data masking techniques for nonlinear operations of the CNN to reduce communication costs. We implemented PPCNN and evaluated its performance on three real-world radiological image datasets. Experimental results show that PPCNN outperforms state-of-the-art methods in mobile cloud scenarios, achieving superior response times and lower usage costs. This study introduces an efficient and privacy-preserving framework for cloud-based medical imaging analysis, marking a significant step towards practical, secure, and trustworthy AI-driven healthcare solutions. •This is the first work to address privacy and latency in CNN inference for medical imaging.•We propose PPCNN, a secure CNN framework combining homomorphic encryption and masking methods.•A coefficient-aware packing method optimizes computation and improves linear layer efficiency.•Extensive experiments show PPCNN outperforms state-of-the-art in time and communication costs.