Paper Key : IRJ************817
Author: Parth Rajput,Naman Kumar Kurmi,Nishant Patel,Saksham Choudhary
Date Published: 02 Apr 2025
Abstract
Cybersecurity threats are constantly evolving, necessitating innovative methods for threat detection and mitigation. This study examines a hybrid approach that combines machine learning (ML) techniques with traditional cybersecurity protocols to enhance threat identification. By utilizing MLs predictive capabilities alongside established security measures, the proposed system seeks to enhance both the accuracy and efficiency of cyber attack detection. The research assesses multiple ML models and security frameworks, demonstrating their effectiveness in reducing false positives and improving response times.By integrating machine learning algorithms with rule-based methodologies, this study develops a powerful tool for cyber attack detection. The system processes network data, identifying correlations among different variables to detect potential threats, thereby strengthening security and resilience against cyber adversaries. Machine learning models, including both supervised and unsupervised algorithms, operate in conjunction with predefined rule-based techniques to establish a robust, multi-layered security framework. This project not only reinforces cybersecurity defenses but also provides valuable insights into network data analysis and cyber threat detection. By advancing threat detection strategies, it contributes to enhancing the security of digital networks and systems in an increasingly interconnected world.