Saved in:
Bibliographic Details
Main Authors: Mazelan, Muhammed El Mustaqeem, Abdul, Noor Hazlina, AlDahoul, Nouar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.09492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917077908979712
author Mazelan, Muhammed El Mustaqeem
Abdul, Noor Hazlina
AlDahoul, Nouar
author_facet Mazelan, Muhammed El Mustaqeem
Abdul, Noor Hazlina
AlDahoul, Nouar
contents Password security plays a crucial role in cybersecurity, yet traditional password strength meters, which rely on static rules like character-type requirements, often fail. Such methods are easily bypassed by common password patterns (e.g., 'P@ssw0rd1!'), giving users a false sense of security. To address this, we implement and evaluate a password strength scoring system by comparing four machine learning models: Random Forest (RF), Support Vector Machine (SVM), a Convolutional Neural Network (CNN), and Logistic Regression with a dataset of over 660,000 real-world passwords. Our primary contribution is a novel hybrid feature engineering approach that captures nuanced vulnerabilities missed by standard metrics. We introduce features like leetspeak-normalized Shannon entropy to assess true randomness, pattern detection for keyboard walks and sequences, and character-level TF-IDF n-grams to identify frequently reused substrings from breached password datasets. our RF model achieved superior performance, achieving 99.12% accuracy on a held-out test set. Crucially, the interpretability of the Random Forest model allows for feature importance analysis, providing a clear pathway to developing security tools that offer specific, actionable feedback to users. This study bridges the gap between predictive accuracy and practical usability, resulting in a high-performance scoring system that not only reduces password-based vulnerabilities but also empowers users to make more informed security decisions.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Password Security Through a High-Accuracy Scoring Framework Using Random Forests
Mazelan, Muhammed El Mustaqeem
Abdul, Noor Hazlina
AlDahoul, Nouar
Cryptography and Security
Artificial Intelligence
Password security plays a crucial role in cybersecurity, yet traditional password strength meters, which rely on static rules like character-type requirements, often fail. Such methods are easily bypassed by common password patterns (e.g., 'P@ssw0rd1!'), giving users a false sense of security. To address this, we implement and evaluate a password strength scoring system by comparing four machine learning models: Random Forest (RF), Support Vector Machine (SVM), a Convolutional Neural Network (CNN), and Logistic Regression with a dataset of over 660,000 real-world passwords. Our primary contribution is a novel hybrid feature engineering approach that captures nuanced vulnerabilities missed by standard metrics. We introduce features like leetspeak-normalized Shannon entropy to assess true randomness, pattern detection for keyboard walks and sequences, and character-level TF-IDF n-grams to identify frequently reused substrings from breached password datasets. our RF model achieved superior performance, achieving 99.12% accuracy on a held-out test set. Crucially, the interpretability of the Random Forest model allows for feature importance analysis, providing a clear pathway to developing security tools that offer specific, actionable feedback to users. This study bridges the gap between predictive accuracy and practical usability, resulting in a high-performance scoring system that not only reduces password-based vulnerabilities but also empowers users to make more informed security decisions.
title Enhancing Password Security Through a High-Accuracy Scoring Framework Using Random Forests
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2511.09492