<![CDATA[Password security is a critical cybersecurity challenge due to the prevalence of user-generated weak credentials, so automated evaluation methods are needed. This paper develops a Random Forest classification model to predict password strength based on two main features, namely password length and Shannon entropy, trained on a large-scale public dataset. The model achieved a classification accuracy of 91.5% on the test data, where feature importance analysis identified entropy as the most significant predictor. The resulting high-accuracy model is suitable for integration into real-time password strength feedback systems and provides a quantitative basis for formulating stronger security policies.]]>
Copyrights © 2023
