Hybrid Multi-Factor Authentication (MFA) Using Biometrics and Behavioral Analysis

In the modern digital landscape, protecting identities and securing access to sensitive information has become increasingly critical due to the growing risks of data tampering, theft, and impersonation Multi-Factor Authentication (MFA) is an effective solution when numerous authentication methods are integrated This study introduces a Hybrid MFA system that integrates facial biometrics with behavioral analysis to enhance web service security Taking use of the unique and reliable characteristics of physiological biometrics, the system uses facial recognition as its first line of defense using Convolutional Neural Networks (CNNs). To counteract potential vulnerabilities such as spoofing, a second layer evaluates Keystroke Dynamics (KD), which captures unique typing behaviors, including dwell time and typing speed. The shortcomings of singlefactor authentication methods are addressed by this two-layer strategy, which strikes a balance between user ease and security. The sequential verification process begins with facial recognition, followed by behavioral analysis, creating a reliable framework for controlling access. By merging advanced deep learning techniques with behavioral biometrics, this system offers an innovative solution for minimizing password-related security breaches and improving identity verification in online environments. The findings highlight the value of combining physiological and behavioral biometrics to strengthen authentication processes, reduce unauthorized access risks, and tackle challenges associated with privacy, spoofing, and data security.