Weak, reused, and simple passwords lead to the greatest security concern in cybersecurity since they can encourage unauthorized access, identity theft, or data breaches. Many platforms enforce password policies, but users frequently ignore secure password practices because of low awareness or usability issues. This research proposes a machine learningbased solution to assess password strength and provide users with an increased level of awareness to mitigate the risk of cyber attacks. Password strength classification based on password features. In this research, the authors employ password-related characteristics like password length, character diversity (uppercase letters, lowercase letters), digits, and special symbols to classify passwords. We implemented and evaluated four classification models, which were XGBoost, Support Vector Machine, Naïve Bayes, and the proposed model PassDefenderX. Our data set was cleaned, encoded, and separated into a training and testing set in a ratio of 80:20. The experimental results demonstrated that PassDefender X performed the best with an accuracy of 97.15 %, precision of 0.9713, recall of 0.9715, and F1-score of 0.9714, respectively. PassDefender X generated more balanced and robust results when compared with other models. In conclusion, the results from this study show that machine learning has a good capability of recognizing the weak patterns of passwords, and it can help build awareness among users so they have less exposure to cyber threats through compromises on their passwords.