Welcome to the InfoSci Platform
Privacy Preservation of Image Data With Machine Learning

Privacy Preservation of Image Data With Machine Learning

Chhaya Suryabhan Dule, Rajasekharaiah K. M.
Copyright: © 2022 |Pages: 27
ISBN13: 9781799894308|ISBN10: 1799894304|ISBN13 Softcover: 9781799894315|EISBN13: 9781799894322
DOI: 10.4018/978-1-7998-9430-8.ch010
Cite Chapter Cite Chapter

MLA

Dule, Chhaya Suryabhan, and Rajasekharaiah K. M. "Privacy Preservation of Image Data With Machine Learning." Applications of Machine Learning and Deep Learning for Privacy and Cybersecurity, edited by Victor Lobo and Anacleto Correia, IGI Global, 2022, pp. 189-215. https://doi.org/10.4018/978-1-7998-9430-8.ch010

APA

Dule, C. S. & M., R. K. (2022). Privacy Preservation of Image Data With Machine Learning. In V. Lobo & A. Correia (Eds.), Applications of Machine Learning and Deep Learning for Privacy and Cybersecurity (pp. 189-215). IGI Global. https://doi.org/10.4018/978-1-7998-9430-8.ch010

Chicago

Dule, Chhaya Suryabhan, and Rajasekharaiah K. M. "Privacy Preservation of Image Data With Machine Learning." In Applications of Machine Learning and Deep Learning for Privacy and Cybersecurity, edited by Victor Lobo and Anacleto Correia, 189-215. Hershey, PA: IGI Global, 2022. https://doi.org/10.4018/978-1-7998-9430-8.ch010

Export Reference

Mendeley
Favorite

Abstract

The methods used to predict, categorize, and recognize complex data like pictures, audio, and texts have been popular in machine learning. These methods are the basis for future AI-driven internet providers because of unparalleled precision in deep learning methodologies. Commercial firms gather large-scale user data and perform machine learning technique. The massive information necessary for machine learning raises privacy problems. The user's personal and extremely sensitive data such as photographs and voice records are gathered and retained forever by these commercial firms and users can not limit the intents of these sensitive information. In addition, centrally stored data is susceptible to legal and extrajudicial monitoring. Many data owners use profound extensive learning by security and confidentiality. This chapter contains a practical approach that allows several parties to learn a precise model of complex systems for a specific purpose without disclosing their data sets. It provides an interesting element in utility and privacy.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.