Comparative Analysis of Advanced Machine Learning Models for Exploit Detection in Intrusion Detection Systems

The integrity of network infrastructure against malicious exploit attacks relies mostly on Intrusion Detection Systems (IDS). These techniques are very essential for identifying and lowering threats before they start to cause significant damage. This manuscript evaluates three advanced Machine Learning (ML) models CatBoost, XGBoost, and Long Short-Term Memory (LSTM) on a real-world network traffic dataset to determine their suitability for IDS applications. Every model is evaluated using key metrics: accuracy, precision, recall, F1-score, and error measures including Root Mean Squared Error (RMSE) and Mean Squared Error (MSE). Based on the results, Catboost exceeds the other models with a 98.55% accuracy and lowest error rates. Given CatBoost's remarkable performance, it is very fitting for real-time IDS systems where reducing false positives and false negatives is extremely crucial. XGBoost provides a balanced and computationally affordable solution even if it is significantly less accurate; it is ideal for scenarios requiring fast responses with limited resources. Strong in sequential pattern recognition, LSTM has a higher rate of false positives, suggesting that further tuning is needed to improve its accuracy and overall reliability in real-time surroundings. The possibility of enhancing the IDS performance of gradient boosting models such as XGBoost and CatBoost in cybersecurity is underlined in this study.