Ai driven Multiple fake account detection using deep learning techniques
Year: 2025
Type: article
Abstract: The increasing prevalence of fake accounts on digital platforms poses major challenges related to identity fraud, cybercrime, and data integrity. Existing verification mechanisms, such as email registration and OTP authentication, are often bypassed using disposable emails and unregistered phone numbers. To address this issue, we propose an AI-driven system for fake account detection using Aadhaar-based identity verification combined with deep learning techniques. The system integrates Aadhaar-linked email and mobile number validation during user registration, ensuring higher authenticity. An Artificial Neural Network (ANN) is employed to classify accounts by analyzing structured identity features and behavioral patterns. The model undergoes preprocessing, normalization, and is trained to distinguish between genuine and suspicious accounts with high accuracy. Experimental results highlight the effectiveness of the proposed system in identifying multiple fake profiles with minimal false positives. This approach enhances user security and can be applied to various domains, including social media, e-commerce, and e-governance, where verified digital identity is critical.
Authors: Jeevitha K, Dr. V Poornima
Institution: Vels University
Language: English
Topic: Spam and Phishing Detection
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6912026959
FWCI:
Cites:
Cited by:
Related to: