In recent years, Online Social Networks (OSNs) have become an essential part of our daily life. In the present generation, OSNs have gained immense popularity, with individuals increasingly intertwining their social interactions with these platforms. People rely on OSNs to stay connected, share information and often manage online business. However, the rapid expansion of OSNs and the widespread sharing of personal data have made these platforms prime targets for attackers to steal their information. In this article, we focus on addressing the issue of profile cloning, a significant threat to user privacy and trust in OSNs. We propose and evaluate various machine learning algorithms to detect and mitigate this issue. Our findings highlight that modern machine learning algorithms like CatBoost and LightGBM significantly outperform several other regression and classification models, demonstrating its effectiveness in accurately detecting profile cloning instances. This study underscores the potential of machine learning in safeguarding OSNs against evolving security threats.