Efficient Network Anomaly Detection and Mitigation Strategies for Large-scale Networks
Dheerender Thakur, Krishna Prasath Sivaraj, Monali Gulhane, Jaswanth Alahari, Rakesh Jena, Punit Goel · 2025
Efficient Network Anomaly Detection and Mitigation Strategies for Large-scale Networks As the number of connected devices has increased so has the potential for malicious activities and network malfunctions. This study focuses on creating efficient mechanisms for real-time and accurate detection and avoidance of outliers in big Abstract-Efficient Strategies to Detect and Mitigate Network Anomalies in Large-scale Networks As more and more devices get connected to the internet, the chances of malicious activities and network failures only increase. To address this problem, this study develops efficient mechanisms for detecting and avoiding outliers in big data networks in real time and with high accuracy. The approaches proposed will utilize techniques as machine learning, data mining and network traffic analytics. The next step is to build out anomaly detection models that can identify and classify abnormal network behavior using these techniques. In addition, the methods will employ advanced data processing tools to detect vast quantities of network data in real-time to minimize false positive rates." Active learning theory: efficient and scalable, deployable to large-scale networks, anomaly detection and remediation methods. L7-QoS takes even the network one step ahead and thus increases the network quality by significantly decreasing the ratio of the hazardous operation or the error of the system. This work has important implications to any sector or organization where large-scale networks are important--including telecommunications, banking, and healthcare.