Survey on Machine Learning with Cloud Technology Preserving Privacy: Risks and Keys

Authors

  • Dr. Harikrishna Bommala, Jajjara Bhargav, Venkata Rao Yanamadni, Nagineni Srinivas, Dr. S. Kiran

Abstract

Increasingly, Machine Learning (ML), from intrusion sensing to proposing new techniques, has been used in several applications. Certain ML applications require info for private persons. Such personal info is uploaded for removing leanings and building modules from central locations of plain text for ML algorithms. The issue is not limited to threats to insider threats to these businesses or external threats to private info that is exposed to hacking by companies keeping the info sets. In order to address privacy problems effectively in current machine training schemes, the information gap among ML, and Privacy Communities (PC) needs to be associated. The elucidations can be supplied with a variety of Control-Based Technology (CBT) to address various security problems, threats, and assaults, such as next-generation firewalls, encryption methods, Intrusion Detection (ID), software-defined networks and ML technologies, etc. The aim of this article is to concentrate on the info protection approaches in the cross-section of both fields. The purpose is to tie the gap between machine training, info protection, and security.

Keywords- cloud security ; machine learning, threats, attacks, Intrusion Detection

Published

2021-02-28

Issue

Section

Articles