EXPLORING THE POTENTIAL OF ARTIFICIAL INTELLIGENCE TO PREDICT CYBER ATTACKS: CREATION, EVALUATION AND COMPARATIVE ANALYSIS OF EFFECTIVE MODELS OF FINE-TUNING, RANDOM FORESTS, AND NEURAL NETWORKS

This quantitative investigation focuses on the application of artificial intelligence (AI) models for predicting cyberattacks and detecting anomalies in network traffic, aiming to enhance cybersecurity defenses. With the increasing complexity of cyber threats, AI offers a promising solution to address these challenges by providing predictive and responsive capabilities. This study compares three AI models — Fine-Tuning, Random Forests, and TensorFlow — using datasets aggregated on daily, weekly, and monthly levels. The methodology includes advanced data preprocessing, statistical analysis, and evaluation metrics such as RMSE, R², Precision, Recall, and F1-Score. Random Forests demonstrated exceptional accuracy and reliability, achieving high R² values and minimal errors. Fine-Tuning showed strong predictive capabilities but required careful parameter tuning to maintain accuracy. TensorFlow proved to be a powerful tool but required optimization to improve precision and reduce false positives. These results highlight the importance of model selection and parameter tuning in AI-driven cybersecurity applications.