Machine Learning-Based Password Vulnerability Detection and Strength Assessment System for Consumer Wi-Fi Routers

The improvement of consumer-grade Wi-fi routers greatly ascertained wide access to the global internet, though with numerous security challenges. Thus, existing research evidence confirmed that many users maintain weak passwords, while routers firmware were left outdated and lots of security misconfiguration settings. However, these security flaws were exploited by various attack mechanisms such as brute force attacks, phishing attacks among others, leading to invasion of user’s privacy and campaign launch for distributed denial-of-service (DDoS). Notably, this research developed Secured Router Security Assessment System (SRSAS), applying a machine learning mechanism for evaluating Wi-Fi router password authentications. The system, however, classified the password authentication into three different categories such as Weak, Good and Strong. Similarly, the system used 60,000 datasets of labelled passwords to train the models. Hence, improving the reliability of the system incorporated entropy analysis, checking against known data breaches and generating suggestions to the users for stronger passwords. The results show that the system performs well in predicting password strength and in offering realistic advice for improving router security. The work therefore contributes both academically and practically: it demonstrates how machine learning can be applied to real-world network security and gives everyday users a tool for improving the safety of their home routers.