Auto-ML Cyber Security Data Analysis Using Google, Azure and IBM Cloud Platforms
Authors:
- 20 July 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Abstract
Machine Learning can be used with cybersecurity data to protect organizations by using artificial intelligence (AI) to generate rules and models for thread detection. Cloud platforms offer the ability to scale AI efforts as well as automatically generate machine learning models (Auto ML). Adoption of Auto-ML is increasing which is resulting in rapid improvements of the technology. The objective of this paper is to demonstrate the Auto ML functionalities against cyber security threat detection using available tools in free tier accounts created on three different cloud platforms (Microsoft Azure, Google, and IBM). We determined the performance of these tools by the evaluating the optimization speed and accuracy results. A comparison of the advantages of each of the results from the different platforms are presented. Overall, all three platforms performed greater than 70% accuracy with the IBM Cloud Platform having the strongest performance.Keywords
This publication has 19 references indexed in Scilit:
- Intelligent approach to build a Deep Neural Network based IDS for cloud environment using combination of machine learning algorithmsComputers & Security, 2019
- Distributed Machine Learning on IAAS Clouds2018
- Using Azure Maching Learning Cloud Technology for Electric Machines Optimization2018
- Privacy-preserving machine learning with multiple data providersFuture Generation Computer Systems, 2018
- A Semantic Internet of Things Framework using Machine Learning Approach based on Cloud Computing2018
- Machine Learning2018
- Towards evolutionary machine learning comparison, competition, and collaboration with a multi-cloud platform2017
- An Auto-Scaling Framework for Controlling Enterprise Resources on Clouds2015
- A Cloud-Based Experiment Platform for Computer-Based Education2014
- A separate compilation extension to standard ML2006