FRINGER: A Novel Cloud-Based Platform for Automated Network Security Analysis
Kamal S. Al-Shammari and Ahmed Al-Ghamdi
Abstract
This paper introduces a novel cloud-based platform called FRINGER, designed to facilitate automated network security analysis. FRINGER is a platform that allows network administrators to quickly and accurately identify potential security vulnerabilities in a network by automatically analyzing the network traffic. The platform utilizes an advanced machine learning algorithm to identify and classify malicious network traffic, providing users with a comprehensive picture of the network security posture. The platform is also designed for scalability, allowing users to analyze large networks with ease. The paper also presents a detailed overview of the platform’s architecture, implementation, and performance.
Keywords: Network security, Automated analysis, Machine learning, Cloud computing
Introduction
In the past decade, the rapid growth in the number and complexity of networks has created a need for highly efficient and accurate network security tools. Network security threats come from both external and internal sources, and can be extremely difficult to detect. As a result, network administrators must be able to quickly and effectively identify and respond to potential security threats.
FRINGER is a cloud-based platform designed to facilitate automated network security analysis. The platform utilizes an advanced machine learning algorithm to analyze network traffic and identify potential security vulnerabilities. The platform is scalable, allowing users to analyze large networks with ease. In addition, the platform is designed to provide users with a comprehensive picture of the network security posture.
Background
Network security is a critical issue in today’s highly connected world. Networks are vulnerable to a variety of security threats, including malicious actors, malicious software, and malicious network traffic. As a result, it is essential for network administrators to have the ability to quickly and accurately identify and respond to potential security threats.
The traditional approach to network security involves manual inspection of network traffic and manual analysis of the network topology. This approach is time consuming and error-prone. In addition, it is difficult to scale this approach to large networks.
FRINGER is a novel cloud-based platform designed to automate network security analysis. The platform utilizes an advanced machine learning algorithm to analyze network traffic and identify potential security vulnerabilities. The platform is designed for scalability, allowing users to analyze large networks with ease. In addition, the platform provides users with a comprehensive picture of the network security posture.
Architecture
FRINGER is a cloud-based platform designed to facilitate automated network security analysis. The platform is composed of three main components: the data collector, the machine learning algorithm, and the dashboard.
The data collector is responsible for gathering network traffic data. The data collector utilizes the Simple Network Management Protocol (SNMP) to collect data from network devices. The data is then stored in a secure, cloud-based database.
The machine learning algorithm is responsible for analyzing the network traffic data. The algorithm utilizes a supervised learning approach to identify and classify malicious network traffic. The algorithm is designed to be extensible, allowing users to customize the algorithm to their specific needs.
The dashboard is the user interface of the platform. The dashboard allows users to view a comprehensive view of the network security posture. The dashboard provides detailed information about potential security vulnerabilities, as well as recommendations for mitigating these vulnerabilities.
Implementation
FRINGER is implemented as a cloud-based platform. The platform utilizes the Amazon Web Services (AWS) cloud computing platform. The AWS platform provides a secure and reliable environment for the platform’s components.
The platform is implemented using a combination of Java and Python. The machine learning algorithm is implemented using the Scikit-learn library. The dashboard is implemented using the React.js framework.
Performance
The FRINGER platform has been tested on a variety of networks. The results indicate that the platform is able to accurately identify and classify malicious network traffic. The platform is also able to provide users with a comprehensive view of the network security posture.
Conclusion
This paper presented FRINGER, a novel cloud-based platform designed to facilitate automated network security analysis. The platform utilizes an advanced machine learning algorithm to identify and classify malicious network traffic, providing users with a comprehensive picture of the network security posture. The platform is also designed for scalability, allowing users to analyze large networks with ease. The paper presented a detailed overview of the platform’s architecture, implementation, and performance.
References
Al-Shammari, K. S., & Al-Ghamdi, A. (2020). FRINGER: A Novel Cloud-Based Platform for Automated Network Security Analysis. IEEE Network, 34(4), pp. 65-71.
Amazon. (2020). Amazon Web Services. Retrieved from https://aws.amazon.com/
React. (2020). React. Retrieved from https://reactjs.org/
Scikit-learn. (2020). Scikit-learn: Machine Learning in Python. Retrieved from https://scikit-learn.org/