Abstract
One of the main problems of machine learning is the need for a large amount of memory and a long learning time. To solve this problem, many companies prefer to store their data and training models on remote servers. However, not all data and models can be stored in the plaintext without any protection. In many areas (for example, banking or medical), the privacy of data and models is very important. To ensure confidentiality, a privacy-preserving machine learning application is a good solution. This article discusses two main approaches to privacy-preserving machine learning (cryptographic and perturbation), describes methods for ensuring privacy, which they include, and provides examples of using of some methods in practice.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Top Nine Machine Learning Applications in Real World. https://data-flair.training/blogs/machine-learning-applications. Last Accessed 10 Nov 2018
Comparing Machine Learning as a Service: Amazon, Microsoft Azure, Google Cloud AI, IBM Watson. https://www.altexsoft.com/blog/datascience/comparing-machine-learning-as-a-service-amazon-microsoft-azure-google-cloud-ai-ibm-watson. Last Accessed 01 Nov 2018
Seven Machine Learning as a Service Platforms for Beginners and PhDs. https://www.cleveroad.com/blog/mlaas–machine-learning-as-a-service-solutions-that-promise-to-change-the-way-you-code. Last Accessed 05 Nov 2018
Al-Rubaie, M., Morris Chang, J.: Privacy preserving machine learning: threats and solutions. In: Institute of Electrical and Electronics Engineers (IEEE) in IEEE Security & Privacy IEEE Security & Privacy, vol. 17, pp. 49–58 (2019)
Madatov, O.: Some information security problems of cloud data storage. IT Secur. (Russia) 25(3), 45–52 (2018)
Walker, J.: Data leak Down Under: 50,000 gov’t employee records found on open S3 bucket. https://portswigger.net/daily-swig/data-leak-down-under-50-000-govt-employee-records-found-on-open-s3-bucket. Last Accessed 05 Nov 2018
Shaikh, R.: Hackers Stole Over 60 Million Dropbox Accounts—How to Check If You Are Affected, https://wccftech.com/hackers-stole-68m-dropbox-accounts. Last Accessed 15 Nov 2018
Dickson, B.: The security threats of neural networks and deep learning algorithms. https://bdtechtalks.com/2018/12/27/deep-learning-adversarial-attacks-ai-malware. Last Accessed 15 Nov 2018
Warner, S.: Randomized response: a survey technique for eliminating evasive answer bias. J. Am. Stat. Assoc. 60, 63–69 (1965)
Erlingsson, U., Pihur, V., Korolova, A.: RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response. In: Google AL (2014)
Principal Component Analysis Tutorial. https://opendatascience.com/principal-component-analysis-tutorial. Last Accessed 10 May 2019
Vorontsov, K.: Principal component analysis. http://www.machinelearning.ru/wiki/images/archive/a/a2/20150509140209%21Voron-ML-regression-slides.pdf. Last Accessed 10 May 2019
Burtyka, F.: UMPHE: UMPHE: a library for effective computing on encrypted data. IT Secur. (Russia) 23(1), 20–22 (2016)
Will, M.A., Ko, R.: A guide to homomorphic encryption. In: The Cloud Security Ecosystem, pp. 101–127 (2015)
Bellare, M., Hoang, V.T., Rogaway, P.: Foundations of garbled circuits. In: Proceedings of the 19th Annual Conference on Computer and Communications Security. ACM (2012)
Fuko, T.: Intel Software Guard Extensions (SGX) explained. In: 9th International Conference on Computer and Systems Engineering, Germany (2019)
Yum, D.H., Kim, D.S., Kim, J.S., Lee, P.J., Hong, S.J.: Order-Preserving Encryption for Non-uniformly Distributed Plaintexts. In: Computer Vision—ECCV 2012, vol. 7115, pp. 84–97 (2012)
Evaluation of Privacy-Preserving Technologies for Machine Learning. https://outlierventures.io/research/evaluation-of-privacy-preserving-technologies-for-machine-learning. Last Accessed 01 April 2019
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lisin, N., Zapechnikov, S. (2020). Methods and Approaches for Privacy-Preserving Machine Learning. In: Misyurin, S., Arakelian, V., Avetisyan, A. (eds) Advanced Technologies in Robotics and Intelligent Systems. Mechanisms and Machine Science, vol 80. Springer, Cham. https://doi.org/10.1007/978-3-030-33491-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-33491-8_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33490-1
Online ISBN: 978-3-030-33491-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)