MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641024409 A) filed by Dharun Chandru, Coimbatore, Tamil Nadu, on March 1, for 'hybrid machine learning and deep learning framework for social network spam detection.'
Inventor(s) include Jayakumari D S; Shanmuga Priya B; Keerthana S; and Kaviya S.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "The rapid proliferation of social networking platforms has led to a significant rise in spam and fake accounts, posing serious threats to user trust, privacy, and platform integrity. Traditional rule-based detection systems often fail to adapt to evolving spam behaviors. To address this challenge, this work presents an intelligent social network spam detection framework using a hybrid deep learning approach combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The proposed system leverages the CNN component to extract meaningful local patterns from user activity and content, while the BiLSTM module captures sequential dependencies and temporal behaviors in user interactions. The framework integrates advanced feature engineering with scalable learning models to effectively distinguish between genuine and malicious accounts. The hybrid CNN + BiLSTM architecture combines the strengths of feature extraction and sequence learning, improving the system's ability to detect complex spam behaviors. The trained model is deployed for real-time prediction through an interactive dashboard, enabling efficient identification of spam accounts with enhanced accuracy and robustness. Experimental results demonstrate that the proposed hybrid model outperforms standalone machine learning and deep learning approaches in terms of accuracy, precision, recall, and F1-score. This work highlights the effectiveness of hybrid CNN + BiLSTM models in enhancing social network security and provides a scalable, automated solution for spam detection."
Disclaimer: Curated by HT Syndication.
