More Web Proxy on the site http://driver.im/

research-article

Efficient and self-recoverable privacy-preserving k-NN classification system with robustness to network delay

Authors:

Jianfeng MaAuthors Info & Claims

Volume 150, Issue C

https://doi.org/10.1016/j.sysarc.2024.103111

Published: 01 May 2024 Publication History

Abstract

Online classification services based on machine learning have been widely used in fields such as healthcare and finance. To enhance the data privacy and avoid server collusion, companies usually deploy servers on different cloud service providers in distant regions separately, which implies high network delay between servers. However, many existing schemes inevitably involve a large number of communication rounds, resulting in inefficient online performance. To mitigate the negative effect of network delay, we propose an efficient and delay-robust approach for privacy-preserving k-NN classification on two non-interactive servers. Our method utilizes the state-of-the-art homomorphic secret sharing (HSS) technique and only introduces constant communication rounds. We also design an efficient self-recovery mechanism by enabling redundant cloud servers to securely back up the encrypted dataset, which is efficient even under high network delay. As the result of experiments we conducted in various network environment, our scheme is more online-efficient and is more robust to high network delay compared with related works.

Graphical abstract

Display Omitted

Highlights

•

Constant online communication rounds, efficient and robust classification service even under network delay.

•

Secure redundant backup servers to enable fast system self-recovery without data re-upload.

•

Client-friendly and lightweight scheme for low-power IoT devices.

References

[1]

M. Ribeiro, K. Grolinger, M.A. Capretz, Mlaas: Machine learning as a service, in: 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA, 2015.

[2]

Motahari-Nezhad H.R., Stephenson B., Singhal S., Outsourcing business to cloud computing services: Opportunities and challenges, IEEE Internet Comput. 10 (4) (2009).

[3]

Pop D., Machine learning and cloud computing: Survey of distributed and saas solutions, 2016, arXiv preprint arXiv:1603.08767.

[4]

Deekshatulu B., Chandra P., et al., Classification of heart disease using k-nearest neighbor and genetic algorithm, Procedia Technol. 10 (2013).

[5]

Chen Y., Hao Y., A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction, Expert Syst. Appl. 80 (2017).

[6]

Samanthula B.K., Elmehdwi Y., Jiang W., k-Nearest neighbor classification over semantically secure encrypted relational data, IEEE Trans. Knowl. Data Eng. 27 (5) (2015).

[7]

Xie B., Xiang T., Liao X., Access-oblivious and Privacy-Preserving K Nearest Neighbors Classification in dual clouds, Comput. Commun. 184 (2022).

[8]

Elmehdwi Y., Samanthula B.K., Jiang W., Secure k-nearest neighbor query over encrypted data in outsourced environments, in: 2014 IEEE 30th International Conference on Data Engineering, IEEE, 2014, pp. 664–675.

[9]

Choi S., Ghinita G., Lim H.-S., Bertino E., Secure knn query processing in untrusted cloud environments, IEEE Trans. Knowl. Data Eng. 26 (11) (2014).

[10]

Xu R., Morozov K., Yang Y., Zhou J., Takagi T., Efficient outsourcing of secure k-nearest neighbour query over encrypted database, Comput. Secur. 69 (2017).

[11]

H. Feng, J. Llorca, A.M. Tulino, A.F. Molisch, Dynamic network service optimization in distributed cloud networks, in: 2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS, 2016.

[12]

Yuan H., Bi J., Zhou M., Temporal task scheduling of multiple delay-constrained applications in green hybrid cloud, IEEE Trans. Serv. Comput. 14 (5) (2018).

[13]

Augustin A., Yi J., Clausen T., Townsley W.M., A study of LoRa: Long range & low power networks for the internet of things, Sensors 16 (9) (2016).

[14]

Aboubakar M., Kellil M., Roux P., A review of IoT network management: Current status and perspectives, J. King Saud Univ.-Comput. Inf. Sci. (2021).

[15]

Knott B., Venkataraman S., Hannun A., Sengupta S., Ibrahim M., van der Maaten L., Crypten: Secure multi-party computation meets machine learning, Adv. Neural Inf. Process. Syst. 34 (2021).

[16]

Roumani Y., Nwankpa J.K., An empirical study on predicting cloud incidents, Int. J. Inf. Manage. 47 (2019).

[17]

Khan M.A., A survey of security issues for cloud computing, J. Netw. Comput. Appl. 71 (2016).

[18]

Cheraghlou M.N., Khadem-Zadeh A., Haghparast M., A survey of fault tolerance architecture in cloud computing, J. Netw. Comput. Appl. 61 (2016).

[19]

Sharma K., Singh K.R., Online data back-up and disaster recovery techniques in cloud computing: A review, Int. J. Eng. Innov. Technol. (IJEIT) 2 (5) (2012).

[20]

Huang X., Leng S., Maharjan S., Zhang Y., Multi-agent deep reinforcement learning for computation offloading and interference coordination in small cell networks, IEEE Trans. Veh. Technol. 70 (9) (2021).

[21]

C. Orlandi, P. Scholl, S. Yakoubov, The rise of Paillier: homomorphic secret sharing and public-key silent OT, in: Advances in Cryptology–EUROCRYPT 2021: 40th Annual International Conference on the Theory and Applications of Cryptographic Techniques, 2021.

[22]

Cover T., Hart P., Nearest neighbor pattern classification, IEEE Trans. Inform. Theory 13 (1) (1967).

[23]

Liang Y., Li Y., Cao Q., Ren F., VPAMS: Verifiable and practical attribute-based multi-keyword search over encrypted cloud data, J. Syst. Archit. 108 (2020).

[24]

Li Y., Cao Q., Zhang K., Ren F., A secure index resisting keyword privacy leakage from access and search patterns in searchable encryption, J. Syst. Archit. 115 (2021).

[25]

Gou J., Ma H., Ou W., Zeng S., Rao Y., Yang H., A generalized mean distance-based k-nearest neighbor classifier, Expert Syst. Appl. 115 (2019).

[26]

Zhang S., Li J., KNN classification with one-step computation, IEEE Trans. Knowl. Data Eng. 35 (3) (2023).

[27]

Memiş S., Enginoğlu S., Erkan U., Fuzzy parameterized fuzzy soft k-nearest neighbor classifier, Neurocomputing 500 (2022).

[28]

Zhu D., Zhu H., Liu X., Li H., Wang F., Li H., Feng D., CREDO: Efficient and privacy-preserving multi-level medical pre-diagnosis based on ML-kNN, Inform. Sci. 514 (2020).

[29]

Chen H., Chillotti I., Dong Y., Poburinnaya O., Razenshteyn I., Riazi M.S., SANNS: Scaling up secure approximate k-nearest neighbors search, in: USENIX Security, 2020.

[30]

A. Boldyreva, T. Tang, Privacy-Preserving Approximate -Nearest-Neighbors Search that Hides Access, Query and Volume Patterns, in: Proceedings on Privacy Enhancing Technologies, 2021, (4) 2021.

[31]

Xu C., Wang N., Zhu L., Zhang C., Sharif K., Wu H., Reliable and privacy-preserving top-k disease matching schemes for E-healthcare systems, IEEE Internet Things J. 9 (7) (2021).

[32]

Liu Q., Hao Z., Peng Y., Jiang H., Wu J., Peng T., Wang G., Zhang S., SecVKQ: Secure and verifiable kNN queries in sensor–cloud systems, J. Syst. Archit. 120 (2021).

[33]

V.S. Gaikwad, K. Walse, V. Thakare, Privacy preserving outsourced k nearest neighbors classification: comprehensive study, in: Futuristic Trends in Networks and Computing Technologies: Select Proceedings of Fourth International Conference on FTNCT 2021, 2022.

[34]

Park J., Lee D.H., Parallelly running k-nearest neighbor classification over semantically secure encrypted data in outsourced environments, IEEE Access 8 (2020).

[35]

Wu W., Parampalli U., Liu J., Xian M., Privacy preserving k-nearest neighbor classification over encrypted database in outsourced cloud environments, World Wide Web 22 (2019).

[36]

Yang K., Tian C., Xian H., Tian W., Zhang Y., Query on the cloud: Improved privacy-preserving k-nearest neighbor classification over the outsourced database, World Wide Web 26 (4) (2023).

[37]

Tan Y., Wu W., Liu J., Wang H., Xian M., Lightweight edge-based kNN privacy-preserving classification scheme in cloud computing circumstance, Concurr. Comput.: Pract. Exper. 32 (19) (2020).

[38]

Liu L., Su J., Liu X., Chen R., Huang K., Deng R.H., Wang X., Toward highly secure yet efficient KNN classification scheme on outsourced cloud data, IEEE Internet Things J. 6 (6) (2019).

[39]

Haque R.U., Hasan A.S.M.T., Jiang Q., Qu Q., Privacy-preserving K-nearest neighbors training over blockchain-based encrypted health data, Electronics 9 (12) (2020).

[40]

Shen X., Luo X., yuan F., Wang B., Chen Y., Tang D., Gao L., Privacy-preserving multi-party deep learning based on homomorphic proxy re-encryption, J. Syst. Archit. 144 (2023).

[41]

Yang H., Liang S., Ni J., Li H., Shen X.S., Secure and efficient k NN classification for industrial internet of things, IEEE Internet Things J. 7 (11) (2020).

[42]

Altman N.S., An introduction to kernel and nearest-neighbor nonparametric regression, Am. Stat. (1992) 175–185.

[43]

Dudani S.A., The distance-weighted k-nearest-neighbor rule, IEEE Trans. Syst. Man Cybern. (4) (1976).

[44]

E. Boyle, N. Gilboa, Y. Ishai, Breaking the circuit size barrier for secure computation under DDH, in: Annual International Cryptology Conference, 2016.

[45]

E. Boyle, N. Gilboa, Y. Ishai, Group-Based Secure Computation: Optimizing Rounds, Communication, and Computation, in: International Conference on the Theory and Applications of Cryptographic Techniques, 2017.

[46]

H. Morita, N. Attrapadung, T. Teruya, S. Ohata, K. Nuida, G. Hanaoka, Constant-round client-aided secure comparison protocol, in: Computer Security: 23rd European Symposium on Research in Computer Security, ESORICS 2018, 2018.

[47]

Dua D., Graff C., UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences, 2017, URL http://archive.ics.uci.edu/ml.

Recommendations

Privacy preserving smartcard-based authentication system with provable security

In this paper, we suggest a new privacy preserving smartcard-based password authenticated key exchange SC-PAKE with provable security. Only the user who has two secrets smartcard and password can go through authentication with key exchange while ...
Efficient structure-preserving signature scheme from standard assumptions
SCN'12: Proceedings of the 8th international conference on Security and Cryptography for Networks

We present an efficient signature scheme that facilitates Groth-Sahai proofs [25] of knowledge of a message, a verification key, and a valid signature on the message, without the need to reveal any of them. Such schemes are called structure-preserving. ...
A hybrid algorithm for secure cloud computing

Cloud computing is a developing technology that is yet unclear to many security issues. Data in the untrusted clouds can be encrypted using an encryption algorithm. Randomising this data provides more security which can be achieved by padding concept in ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Journal of Systems Architecture: the EUROMICRO Journal

Journal of Systems Architecture: the EUROMICRO Journal Volume 150, Issue C

May 2024

261 pages

Issue’s Table of Contents

Elsevier B.V.

Publisher

Elsevier North-Holland, Inc.

United States

Publication History

Published: 01 May 2024

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 02 Feb 2025

Other Metrics

View Author Metrics

Citations

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents