Fraudulent Login Detection Using AI |
Author(s): |
| Harshitha H B , ATME College Of Engineering; Abhineeth Aalthoor, ATME College Of Engineering; B R Yashaswini, ATME College Of Engineering; C Smriti Emmanuel, ATME College Of Engineering; Kushal Mandivya, ATME College Of Engineering |
Keywords: |
| Anomaly Detection, AI-Based Security, Behavioral Authentication, Fraud Prevention, Machine Learning, Cybersecurity |
Abstract |
|
With the rapid evolution of digital technology, securing user accounts has become an increasingly crucial challenge. Traditional authentication mechanisms, including passwords and static rule-based security protocols, have become vulnerable to cyber threats such as credential stuffing, phishing, and brute-force attacks. This paper presents an AI-powered system to enhance login security by analyzing user behavior and detecting anomalous activities indicative of fraudulent logins. By employing a machine learning-based approach, the system evaluates key factors such as IP address, geographical location, login frequency, and device fingerprinting to detect unauthorized access attempts. The model dynamically adapts to new threats by continuously learning from historical login patterns. The proposed solution enhances cybersecurity while maintaining a seamless user experience by minimizing false positives. |
Other Details |
|
Paper ID: IJSRDV12I120018 Published in: Volume : 12, Issue : 12 Publication Date: 01/03/2025 Page(s): 19-20 |
Article Preview |
|
|
|
|
