Password Authentication Using Modify Multi-Connect Architecture Associative Memory

Traditional password authentication systems often face challenges related to security vulnerabilities, slow authentication speeds, and susceptibility to noise interference. While previous methods such as Multi-Bias Associative Memory (MBAM) have made progress in improving authentication performance, they still suffer from inefficiencies in training time, accuracy, and robustness to noisy input data.To address these limitations, this research introduces an Enhanced Password Authentication System leveraging Modified Multi-Connect Architecture (MMCA) associative memory, supporting both graphical and textual passwords. MMCA enhances pattern recognition, enabling faster and more accurate authentication while ensuring robustness against noise interference. Compared to traditional methods, MMCA reduces computational overhead, improves resistance to adversarial inputs, and accelerates the authentication process.Experimental validation on 100 trials demonstrates 100% authentication accuracy for both graphical and textual password-based methods. The system achieves authentication times of 0.5 seconds for textual passwords and 1 second for graphical passwords, significantly outperforming existing solutions. Additionally, MMCA maintains reliable authentication even in the presence of up to 15% noise in graphical passwords. Comparative analysis shows that MMCA surpasses MBAM and other approaches in training efficiency and authentication speed, making it a promising solution for secure, fast, and noise-resistant user authentication.