Optimization of machine learning methods for de-anonymization in social networks

In recent years, social networks have struggled to meet user protection and fraud prevention requirements under unpredictable risks. Anonymity features are widely used to help individuals maintain their privacy, but they can also be exploited for malicious purposes. In this study, we develop a machine learning-driven de-anonymization system for social networks, with a focus on feature selection, hyperparameter tuning, and dimensionality reduction. Using supervised learning techniques, the system achieves high accuracy in identifying user identities from anonymized datasets. In experiments conducted on real and synthetic data, the optimized models consistently outperform baseline methods on average. Even in cases where they do not, significant improvements in precision are observed. Ethical considerations surrounding de-anonymization are thoroughly discussed, including the responsibility of implementation to maintain a balance between privacy and security. By proposing a scalable and effective framework for analyzing anonymized data in social networks, this research contributes to improved fraud detection and strengthened Internet security.