اخبار و اعلانات

 آمار

تعداد نشریات28
تعداد شماره‌ها876
تعداد مقالات8,481
تعداد مشاهده مقاله17,297,791
تعداد دریافت فایل اصل مقاله11,610,051
Karimi, Mojtaba, Kuhestani, Ali, Keshavarzi, Mohammadreza. (1405). SIP Signaling Anomaly Detection in IMS/VoLTE Networks: A Survey, Taxonomy, and Conceptual Multi-Level Machine Learning Framework. نشریه علمی دانشگاه سیستان و بلوچستان, (), -. doi: 10.22111/ieco.2026.55846.1779
Mojtaba Karimi; Ali Kuhestani; Mohammadreza Keshavarzi. "SIP Signaling Anomaly Detection in IMS/VoLTE Networks: A Survey, Taxonomy, and Conceptual Multi-Level Machine Learning Framework". نشریه علمی دانشگاه سیستان و بلوچستان, , , 1405, -. doi: 10.22111/ieco.2026.55846.1779
Karimi, Mojtaba, Kuhestani, Ali, Keshavarzi, Mohammadreza. (1405). 'SIP Signaling Anomaly Detection in IMS/VoLTE Networks: A Survey, Taxonomy, and Conceptual Multi-Level Machine Learning Framework', نشریه علمی دانشگاه سیستان و بلوچستان, (), pp. -. doi: 10.22111/ieco.2026.55846.1779
Karimi, Mojtaba, Kuhestani, Ali, Keshavarzi, Mohammadreza. SIP Signaling Anomaly Detection in IMS/VoLTE Networks: A Survey, Taxonomy, and Conceptual Multi-Level Machine Learning Framework. نشریه علمی دانشگاه سیستان و بلوچستان, 1405; (): -. doi: 10.22111/ieco.2026.55846.1779

SIP Signaling Anomaly Detection in IMS/VoLTE Networks: A Survey, Taxonomy, and Conceptual Multi-Level Machine Learning Framework

International Journal of Industrial Electronics Control and Optimization
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 24 آبان 1405    اصل مقاله (1.05 M)
نوع مقاله: Review Articles
شناسه دیجیتال (DOI): 10.22111/ieco.2026.55846.1779
نویسندگان
Mojtaba Karimi* 1؛ Ali Kuhestani2؛ Mohammadreza Keshavarzi3
1Qom University of Technology (QUT)
2Faculty of Electrical and Computer Engineering, Qom University of Technology, Qom, Iran
3ICT Research Institute, Iran Telecommunication Research Center (ITRC), Tehran, Iran
چکیده
Session Initiation Protocol (SIP) is a core signaling protocol in IMS and VoLTE networks, supporting user registration, authentication, call setup, session management, and call termination. Abnormal SIP signaling behavior may affect service availability, call setup performance, troubleshooting activities, and the operational stability of IMS components. Existing studies on SIP anomaly detection have addressed flooding, malformed messages, registration abuse, dialog misuse, and machine learning-based detection; however, many approaches remain limited in their ability to jointly consider message-level, temporal-level, transaction-level, dialog-level, error-level, and entity-level behaviors.
This paper presents a survey, taxonomy, and conceptual multi-level machine learning framework for SIP signaling anomaly detection in IMS/VoLTE environments. First, SIP-related anomalies are categorized according to their operational behavior and protocol impact. Then, existing rule-based, statistical, machine learning, deep learning, and federated learning approaches are reviewed and compared in terms of applicability, explainability, data requirements, and operational limitations. Based on the identified gaps, a conceptual six-level feature framework is proposed, covering message, temporal, transaction, dialog, error, and entity features. The framework is intended to support the future development of explainable and data-driven SIP anomaly detection systems.
Since the scope of this work is conceptual rather than experimental, the paper also outlines key research directions for future validation, including controlled IMS/VoLTE testbed implementation, feature extraction from labeled SIP traces, model comparison under class imbalance, and integration of explainability mechanisms for operational use.
کلیدواژه‌ها
VoLTE security؛ Anomaly Mitigation؛ IMS Attacks؛ Telecom Testbed
آمار
تعداد مشاهده مقاله: 1


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب