USE OF ARTIFICIAL NEURAL NETWORK TO IDENTIFY FAKE PROFILES

Kothuri Ashlesha; E.kiran kumar; Dr. P. Venkateshwarlu

doi:10.62643/

Authors

Kothuri Ashlesha Author
E.kiran kumar Author
Dr. P. Venkateshwarlu Author

DOI:

https://doi.org/10.62643/

Keywords:

1. Artificial Neural Network (ANN): A computational model inspired by the human brain, used to learn complex patterns and relationships in data. In this study, ANNs are employed to detect fake profiles automatically. 2. Fake Profile Detection: The process of identifying fraudulent or malicious accounts on social media platforms that may be used for misinformation, spam, or cybercrime. 3. Social Media Security: Measures and technologies designed to protect users and platforms from threats such as fake accounts, cyber-attacks, and unauthorized data access.

Abstract

The rapid growth of social media and online platforms has led to a surge in fake profiles, which are often used for malicious activities such as spreading misinformation, fraud, identity theft, and cyberbullying. Detecting these profiles manually is highly inefficient due to the massive volume of users and the evolving sophistication of fraudulent accounts. This research focuses on leveraging Artificial Neural Networks (ANNs) to automatically identify and classify fake profiles with high accuracy. The proposed approach involves collecting extensive user data, including profile attributes, activity patterns, posting behavior, and social interactions. These features are preprocessed and fed into a multi-layer ANN, which learns complex patterns and relationships that differentiate genuine users from fake accounts. Experimental evaluation demonstrates that the ANN-based system achieves superior detection performance compared to traditional machine learning monitoring tools to proactively prevent the creation and propagation of fraudulent methods, with improved precision, recall, and overall accuracy. The implementation of such intelligent detection models is crucial for enhancing platform security, maintaining user trust, and mitigating the negative social and economic impacts of fake profiles. The study also highlights the potential for integrating this system with real-time accounts.