SocialGuard: An Integrated Framework for Proactive Fake Account Detection Leveraging Behavioral APIs and Malicious URL Profiling

Social media platforms have become indispensable for communication, information dissemination, and business interactions; however, the proliferation of fake accounts threatens user trust, data integrity, and online safety. This study introduces SocialGuard, an integrated framework for proactive fake account detection that combines behavioral API monitoring with malicious URL profiling. The framework extracts hybrid features from user activity, interaction frequency, and external URL patterns, utilizing BERT embeddings for textual behavior and XGBoost for classification. Experiments conducted on a benchmark Kaggle dataset achieved an overall accuracy of 99.51%, outperforming baseline BERT-only models. The results demonstrate that incorporating behavioral dynamics and malicious link profiling significantly enhances the detection of deceptive and automated accounts. This work contributes a scalable, data-driven architecture suitable for real-time deployment in modern social ecosystems.