On this page
Research Article | Open Access
Volume 13 2021 | None
MACHINE LEARNING-DRIVEN CYBER ATTACK DETECTION IN NETWORK ENVIRONMENTS
Shravani.Velpula, Vijayalaxmi.K, Thota Mounika, THIPIRI NITHISH
Pages: 3772-3778
Abstract
This paper presents a novel approach to detecting cyber attacks in network environments using advanced machine learning techniques. With the increasing sophistication of cyber threats, traditional security measures often fall short in identifying and mitigating attacks in real time. Our study employs a range of machine learning algorithms, including Decision Trees, Support Vector Machines, and Neural Networks, to analyze network traffic data and identify patterns indicative of malicious activities. By leveraging a comprehensive dataset of labeled network traffic, we train and validate our models to enhance detection accuracy and reduce false positives. The results demonstrate that machine learning techniques significantly outperform conventional methods in identifying various types of cyber attacks, such as denial of service (DoS), intrusion attempts, and malware propagation. This research contributes to the development of proactive cybersecurity strategies, enabling organizations to enhance their network defenses and respond swiftly to emerging threats.
Keywords
This paper presents a novel approach to detecting cyber attacks in network environments using advanced machine learning techniques.
PDF
26
Views
3
Downloads