• Cara Maria Roma Ravikanth
• Faaziyah Nargis
• Ganta Saathvika
• Mrs. K.V.B. Saraswathi
• Dr. S. JayaLaxmi

Data security is now a number one priority for governments, institutions, and individuals. To support this, we drew on vulnerability information from the CVE database, more specifically Microsoft system vulnerabilities from the past few years. Although predictive cybersecurity studies mainly address the predicament of projecting new attacks, the worldwide impact of postponed patching—most notably in terms of critical infrastructure—is less known. This relative study bridges that gap by proposing a machine learning-based method to predict the "Time to Next Patch" utilizing real-world vulnerability information. Software patching involves a collection of code modifications issued to vendors that aim to eradicate bugs, stabilize security flaws, or enhance prevailing software versions to enhance functionality as well as performance. This paper contrasts several machine learning models—Linear Regression, Random Forest, XGBoost, Gradient Boosting, K-Nearest Neighbors (KNN), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP)—in predicting software patch release time using a dataset of vulnerability data. The 5-fold cross-validation testing demonstrates superior R² scores for Linear Regression and SVR (0.99) indicating very good predictive capability, but if performance measures are also considered, the tree-based models (Random Forest, XGBoost, Gradient Boosting) and MLP showed competitive performance. This study also underscores the importance of cross-validation for evaluating a valid model in predicting software vulnerabilities. This study enables proactive security measures to protect critical systems like power grids and healthcare from preventable breaches. By improving patch timing forecasts, it enhances vulnerability prioritization and speeds up response, reducing exposure time and increasing resilience.

Cybersecurity, Software Updates, Patch Delays, Predictive Modeling, Random Forest Model,Cybersecurity, Patch Delays, Predictive Modeling, Machine Learning, MLP, XGBoost, Gradient Boosting, Support Vector Regressor, K-Nearest Neighbors, Microsoft, CVE database

"AI FOR PROACTIVE CYBERSECURITY : PREDICTING SOFTWARE PATCH RELEASE TIMES TO ENHANCE SOCIETAL RESILIENCE ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.422-431, May-2025, Available :http://www.jetir.org/papers/JETIRGV06063.pdf

"AI FOR PROACTIVE CYBERSECURITY : PREDICTING SOFTWARE PATCH RELEASE TIMES TO ENHANCE SOCIETAL RESILIENCE ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. pp422-431, May-2025, Available at : http://www.jetir.org/papers/JETIRGV06063.pdf