An Efficient Privacy-preserving Deep Learning Scheme for Medical Image Analysis

Document Type : Special Issue: The Importance of Human Computer Interaction: Challenges, Methods and Applications

Authors

1 Ph.D. Candidate, School of Computer Science and Engineering, Vellore Institute of Technology, India.

2 Assistant Professor, School of Information Technology and Engineering, Vellore Institute of Technology, India.

Abstract

In recent privacy has emerged as one of the major concerns of deep learning, since it requires huge amount of personal data. Medical Image Analysis is one of the prominent areas where sensitive data are shared to a third party service provider. In this paper, a secure deep learning scheme called Metamorphosed Learning (MpLe) is proposed to protect the privacy of images in medical image analysis. An augmented convolutional layer and image morphing are two main components of MpLe scheme. Data providers morph the images without privacy information using image morphing component. The human unrecognizable image is then delivered to the service providers who then apply deep learning algorithms on morphed data using augmented convolution layer without any performance penalty. MpLe provides sturdy security and privacy with optimal computational overhead. The proposed scheme is experimented using VGG-16 network on CIFAR dataset. The performance of MpLe is compared with similar works such as GAZELLE and MiniONN and found that the MpLe attracts very less computational and data transmission overhead. MpLe is also analyzed for various adversarial attack and realized that the success rate is as low as . The efficiency of the proposed scheme is proved through experimental and performance analysis.

Keywords

References

Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep Learning with Differential Privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security - CCS’16, 308–318. https://doi.org/10.1145/2976749.2978318
Al, M., Chanyaswad, T., & Kung, S.-Y. (2018). Multi-Kernel, Deep Neural Network and Hybrid Models for Privacy Preserving Machine Learning. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2891–2895. https://doi.org/10.1109/ICASSP.2018.8462336
Alguliyev, R. M., Aliguliyev, R. M., & Abdullayeva, F. J. (2019). Privacy-preserving deep learning algorithm for big personal data analysis. Journal of Industrial Information Integration. https://doi.org/10.1016/j.jii.2019.07.002
Andrew, J., & Kathrine, G. J. W. (2018). An intrusion detection system using correlation, prioritization and clustering techniques to mitigate false alerts. In Advances in Intelligent Systems and Computing (Vol. 645). https://doi.org/10.1007/978-981-10-7200-0_23
Andrew, J., Mathew, S. S., & Mohit, B. (2019). A Comprehensive Analysis of Privacy-preserving Techniques in Deep learning based Disease Prediction Systems. 0–9. https://doi.org/10.1088/1742-6596/1362/1/012070
Andrew J, & Karthikeyan J. (2019). Privacy-Preserving Internet of Things: Techniques and Applications. International Journal of Engineering and Advanced Technology (IJEAT), 8(6), 3229–3234. https://doi.org/10.35940/ijeat.F8830.088619
Biryukov, A., De Cannière, C., Winkler, W. E., Aggarwal, C. C., Kuhn, M., Bouganim, L., Guo, Y., Preneel, B., Bleumer, G., Helleseth, T., Canetti, R., Varia, M., Peters, C., Kaliski, B., Desmedt, Y., Kesidis, G., De Soete, M., Bleumer, G., Schoenmakers, B., … Smith, S. W. (2011). Differential Privacy. In Encyclopedia of Cryptography and Security (pp. 338–340). Springer US. https://doi.org/10.1007/978-1-4419-5906-5_752
Cui, L., Huang, S., Wei, F., Tan, C., Duan, C., & Zhou, M. (n.d.). SuperAgent: A Customer Service Chatbot for E-commerce Websites. 97–102. https://doi.org/10.18653/v1/P17-4017
Ding, X., Yang, W., Raymond Choo, K.-K., Wang, X., & Jin, H. (2019). Privacy preserving similarity joins using MapReduce. Information Sciences, 493, 20–33. https://doi.org/10.1016/J.INS.2019.03.035
Dorner, S., Cammerer, S., Hoydis, J., & Brink, S. Ten. (2018). Deep Learning Based Communication over the Air. IEEE Journal on Selected Topics in Signal Processing, 12(1), 132–143. https://doi.org/10.1109/JSTSP.2017.2784180
Gentry, C., & Boneh, D. (2009). A fully homomorphic encryption scheme. http://cs.au.dk/~stm/local-cache/gentry-thesis.pdf
Goldreich, O. (1998). Secure Multi-Party Computation.
Hesamifard, E., Takabi, H., Ghasemi, M., & Jones, C. (2017). Privacy-preserving Machine Learning in Cloud. Proceedings of the 2017 on Cloud Computing Security Workshop - CCSW ’17. https://doi.org/10.1145/3140649.3140655
J, A., Karthikeyan, J., & Jebastin, J. (2019). Privacy Preserving Big Data Publication On Cloud Using Mondrian Anonymization Techniques and Deep Neural Networks. 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), 722–727. https://doi.org/10.1109/ICACCS.2019.8728384
Juvekar, C., Mtl, M., Vaikuntanathan, V., & Chandrakasan, A. (n.d.). GAZELLE: A Low Latency Framework for Secure Neural Network Inference. Retrieved August 9, 2020, from https://www.usenix.org/conference/usenixsecurity18/presentation/juvekar
Krizhevsky, A., Hinton, G., & others. (2009). Learning multiple layers of features from tiny images.
Li, J., Kuang, X., Lin, S., Ma, X., & Tang, Y. (2020). Privacy preservation for machine learning training and classification based on homomorphic encryption schemes. Information Sciences, 526, 166–179. https://doi.org/10.1016/j.ins.2020.03.041
Li, P., Li, J., Huang, Z., Li, T., Gao, C.-Z., Yiu, S.-M., & Chen, K. (2017). Multi-key privacy-preserving deep learning in cloud computing. Future Generation Computer Systems, 74, 76–85. https://doi.org/10.1016/J.FUTURE.2017.02.006
Li, P., Li, T., Ye, H., Li, J., Chen, X., & Xiang, Y. (2018). Privacy-preserving machine learning with multiple data providers. Future Generation Computer Systems, 87, 341–350. https://doi.org/10.1016/J.FUTURE.2018.04.076
Li, T., Li, X., Zhong, X., Jiang, N., & Gao, C. (2019). Communication-efficient outsourced privacy-preserving classification service using trusted processor. Information Sciences, 505, 473–486. https://doi.org/10.1016/J.INS.2019.07.047
Li, Y., Wang, Y., & Li, D. (2019). Privacy-preserving lightweight face recognition. Neurocomputing, 363, 212–222. https://doi.org/10.1016/J.NEUCOM.2019.07.039
Liang, J., Mahler, J., Laskey, M., Li, P., & Goldberg, K. (2018). Using dVRK teleoperation to facilitate deep learning of automation tasks for an industrial robot. IEEE International Conference on Automation Science and Engineering, 2017-August, 1–8. https://doi.org/10.1109/COASE.2017.8256067
Liu, J., Juuti, M., Lu, Y., & Asokan, N. (n.d.). Oblivious Neural Network Predictions via MiniONN transformations. Retrieved August 9, 2020, from http://rodrigob.github.io/are_we_there_yet/build/classification_datasets_results.
Ma, X., Zhang, F., Chen, X., & Shen, J. (2018). Privacy preserving multi-party computation delegation for deep learning in cloud computing. Information Sciences, 459, 103–116. https://doi.org/10.1016/J.INS.2018.05.005
Ma, Z., Ma, J., Miao, Y., & Liu, X. (2019). Privacy-preserving and high-accurate outsourced disease predictor on random forest. Information Sciences, 496, 225–241. https://doi.org/10.1016/J.INS.2019.05.025
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018). Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics, 19(6), 1236–1246.
Phan, N. H., Vu, M. N., Liu, Y., Jin, R., Dou, D., Wu, X., & Thai, M. T. (2019). Heterogeneous Gaussian mechanism: Preserving differential privacy in deep learning with provable robustness. IJCAI International Joint Conference on Artificial Intelligence, 2019-Augus(June), 4753–4759. https://doi.org/10.24963/ijcai.2019/660
Phong, L. T., & Phuong, T. T. (2019). Privacy-Preserving Deep Learning via Weight Transmission. IEEE Transactions on Information Forensics and Security, 1–1. https://doi.org/10.1109/TIFS.2019.2911169
Rahim, N., Ahmad, J., Muhammad, K., Sangaiah, A. K., & Baik, S. W. (2018). Privacy-preserving image retrieval for mobile devices with deep features on the cloud. Computer Communications, 127, 75–85. https://doi.org/10.1016/J.COMCOM.2018.06.001
Sagirlar, G., Carminati, B., & Ferrari, E. (2018). Decentralizing privacy enforcement for Internet of Things smart objects. Computer Networks, 143, 112–125. https://doi.org/10.1016/J.COMNET.2018.07.019
Shen, D., Wu, G., & Suk, H.-I. (2017). Deep Learning in Medical Image Analysis. Annual Review of Biomedical Engineering, 19(1), 221–248. https://doi.org/10.1146/annurev-bioeng-071516-044442
Shokri, R., & Shmatikov, V. (2015). Privacy-preserving deep learning. 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), 909–910. https://doi.org/10.1109/ALLERTON.2015.7447103
Wang, J., Zhu, X., Zhang, J., Cao, B., Bao, W., & Yu, P. S. (2018). Not just privacy: Improving performance of private deep learning in mobile cloud. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2407–2416. https://doi.org/10.1145/3219819.3220106
Wang, W., Li, S., Dou, J., & Du, R. (2020). Privacy-preserving mixed set operations. Information Sciences, 525, 67–81. https://doi.org/10.1016/j.ins.2020.03.049
Wang, Y., Adams, S., Beling, P., Greenspan, S., Rajagopalan, S., Velez-Rojas, M., Mankovski, S., Boker, S., & Brown, D. (2018). Privacy Preserving Distributed Deep Learning and Its Application in Credit Card Fraud Detection. 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/ 12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE), 1070–1078. https://doi.org/10.1109/TrustCom/BigDataSE.2018.00150
Xiong, L., & Dong, D. (2019). Reversible data hiding in encrypted images with somewhat homomorphic encryption based on sorting block-level prediction-error expansion. Journal of Information Security and Applications, 47, 78–85. https://doi.org/10.1016/j.jisa.2019.04.005
Yang, G., Cao, J., Chen, Z., Guo, J., & Li, J. (2020). Graph-based neural networks for explainable image privacy inference. Pattern Recognition, 105, 107360. https://doi.org/10.1016/j.patcog.2020.107360
Zhang, D., Chen, X., Wang, D., & Shi, J. (2018). A Survey on Collaborative Deep Learning and Privacy-Preserving. 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), 652–658. https://doi.org/10.1109/DSC.2018.00104
Zhang, Q., Yang, L. T., & Chen, Z. (2016). Privacy Preserving Deep Computation Model on Cloud for Big Data Feature Learning. IEEE Transactions on Computers, 65(5), 1351–1362. https://doi.org/10.1109/TC.2015.2470255

Files

Share

How to cite

Statistics