Trust-Aware Federated Learning for Robust and Secure Social Media Analysis

Abstract

The rapid growth of social media requires privacy-preserving approaches for detecting toxic, fraudulent, misleading, and inappropriate content while protecting sensitive user information. This paper proposes a trust-aware federated learning framework that enables collaborative model training without sharing raw user data. An attention-based Long Short-Term Memory (LSTM) network captures important semantic relationships in textual content, while a trust scoring mechanism identifies unreliable or potentially malicious clients. A blockchain layer provides secure verification of model updates and enhances transparency throughout the federated training process. Experimental results demonstrate strong classification performance with limited blockchain overhead, highlighting the framework’s potential as a scalable, secure, and efficient solution for privacy-preserving social media content analysis.