Next-Gen Multiservice Security Based on Behavioral Analytics
Jamal Rzayev1* , Samad Ramazanov1
Abstract. The rapid convergence of voice, video, and data in next-generation networks (NGNs) has rendered traditional signature-based security mechanisms obsolete, as they introduce significant latency and fail to detect zero-day vulnerabilities. This study proposes a novel security methodology for multiservice communication networks based on User and Entity Behavior Analytics (UEBA) and machine learning algorithms. The primary objective is to ensure robust protection of subscriber data without compromising Quality of Service (QoS) parameters. The research employs a telemetry-driven approach, analyzing network flow metadata to establish baseline behavioral profiles for legitimate traffic. Deviations from these baselines, indicative of malicious activities such as distributed denial-of-service (DDoS) attacks or unauthorized data exfiltration, are identified in real-time. The results demonstrate that transitioning from deterministic perimeter defense to probabilistic behavioral monitoring significantly enhances threat detection accuracy while minimizing cryptographic overhead. The proposed framework dynamically allocates security resources, thereby maintaining optimal throughput for delay-sensitive multimedia sessions. Ultimately, integrating behavioral analytics into the architectural core of unified communications provides a resilient, adaptive, and highly scalable defense mechanism against emerging cyber threats.
Keywords: multiservice networks, behavioral analytics, user data security, quality of service, machine learning, anomaly detection