Logistic Regression-Driven Real-Time Cyberattack Identification Using Blockchain for Enhanced Data Security

The increasing sophistication of cyber-attacks on critical defense infrastructures requires advanced, adaptive security frameworks that can detect and respond to emerging threats. This project focuses on developing a cybersecurity framework that leverages machine learning (ML) and blockchain technology to protect intranet systems from behavior-based attacks. Using the "Hydras" dataset from Kaggle, which contains network traffic data for detecting malicious behavior, this framework applies several machine learning algorithms—Logistic Regression (LR), Naïve Bayes (NB), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB). These algorithms are evaluated with K-fold cross-validation to predict whether a given network activity represents a security breach or benign behavior. By integrating AI-driven attack detection, the system can swiftly classify and alert administrators to potential intrusions, improving response times and minimizing damage. In addition to AI-based threat detection, blockchain technology is utilized for secure user authentication during login processes. This integration ensures that user data remains secure and tamper-resistant, preventing unauthorized access and enhancing overall system integrity. The backend is developed using Python, while the frontend is built with HTML, CSS, and JavaScript to provide an intuitive user interface. This adaptive cybersecurity framework aims to bolster the defense of critical infrastructure by combining AI's predictive power with blockchain's immutable security, creating a robust solution for mitigating both known and unknown cyber threats.

Keywords: Cybersecurity, AI, Blockchain, Machine Learning, Behavior-Based Attacks, Intrusion Detection, Critical Infrastructure, Data Security, Hydras Dataset, K-fold Cross Validation, Logistic Regression, Naïve Bayes, K-Nearest Neighbors, Support Vector Machine, Random Forest, Gradient Boosting, Python, HTML, CSS, JavaScript.