Combating SIM Swap Fraud in Telecommunications: A Machine Learning Approach and Multi-Factor Authentication as a Preventive Strategy

Abstract

SIM swap fraud has emerged as a critical threat in the telecommunications sector, enabling attackers to bypass traditional security mechanisms and gain control of users' phone numbers. This paper examines SIM swap fraud as a growing challenge and explores the application of machine learning algorithms for its detection. Additionally, it presents multi-factor authentication (MFA) as an essential preventive measure. The integration of intelligent detection systems and robust authentication protocols is proposed as a dual-layered defence strategy for telecom operators aiming to reduce customer vulnerability and minimize financial losses. The results demonstrate that integrating machine learning-based anomaly detection with multi-factor authentication effectively mitigates SIM swap fraud, reducing fraudulent attempts by 80% and enhancing overall network security and resilience.