DATA SECURITY AND PRIVACY IN DATA COMMUNICATION USING MACHINE LEARNING TECHNIQUES

Abstract

The escalating volume and sensitivity of data transmitted across networks underscore the critical need for robust data security and privacy measures. This research leverages the CICIDS2017 dataset, a comprehensive collection of network traffic data, to investigate key challenges in securing data communication. The study focuses on the identification and classification of network intrusions, the evaluation of intrusion detection systems (IDS), and the assessment of privacy-preserving techniques. The CICIDS2017 dataset enables a detailed analysis of various attack scenarios, providing insights into network vulnerabilities and the effectiveness of different security protocols. The methodology incorporates established techniques from existing literature. The findings contribute to a deeper understanding of the trade-offs between security and privacy, offering recommendations for the design and implementation of more secure and privacy-aware data communication systems. The aim is to enhance the protection of sensitive information in modern network environments.