Abstract :

The Rapid Growth Of Social Networks In India Has Significantly Increased Digital Interactions, But It Has Also Led To The Rise Of Fake Profiles And Botnets That Threaten User Privacy, Spread Misinformation, And Manipulate Public Opinion. Traditional Machine Learning Techniques Often Fail To Capture The Complex Relationships And Structural Dependencies Present In Social Network Data. To Address This Challenge, This Study Proposes A Graph Neural Network (GNN)-based Approach For Detecting Fake Profiles And Botnet Activities In Social Media Platforms. GNNs Are Capable Of Learning From Graph-structured Data By Analyzing Nodes (users) And Edges (connections), Enabling More Accurate Identification Of Suspicious Behavior Patterns. The Proposed System Constructs A Social Graph Where Each Node Represents A User And Edges Represent Interactions Such As Follows, Messages, Or Likes. Features Such As User Activity, Connectivity Patterns, And Behavioral Attributes Are Extracted And Processed. The GNN Model Is Trained To Classify Nodes As Genuine Users Or Malicious Entities. Experimental Results Demonstrate That GNN-based Models Outperform Traditional Classifiers In Terms Of Accuracy, Precision, Recall, And F1-score. The System Is Implemented Using Python-based Frameworks, With Training Conducted In Jupyter Notebook And Deployment Through A Web Interface. This Research Provides An Effective And Scalable Solution For Enhancing Cybersecurity In Indian Social Networks By Detecting And Mitigating Fake Profiles And Botnet Attacks.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1786-1792

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite