• J. Bindhu Bhargavi

The increasing frequency and sophistication of cyber attacks pose a significant threat to modern digital infrastructures, necessitating the development of robust and adaptive detection mechanisms. This study evaluates the effectiveness of various machine learning (ML) models in identifying and classifying cyber attacks across multiple network environments. A comparative analysis was conducted using supervised and unsupervised learning algorithms including Decision Trees, Random Forests, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Deep Neural Networks trained on benchmark intrusion detection datasets such as NSL-KDD and CICIDS2017. Performance metrics including accuracy, precision, recall, F1-score, and detection latency were analyzed to assess model reliability and scalability. Experimental results demonstrate that ensemble-based models, particularly Random Forest and Gradient Boosting, achieve superior detection rates and generalization capabilities compared to traditional classifiers. However, deep learning models exhibit improved adaptability to complex, evolving attack patterns at the cost of higher computational overhead. The findings underscore the potential of hybrid and ensemble approaches in achieving a balanced trade-off between accuracy and efficiency for real-time cyber threat detection. This research contributes insights into the selection and optimization of ML models for practical deployment in intrusion detection systems (IDS).

Machine Learning, Cybersecurity, Intrusion Detection System (IDS), Cyber Attack Detection, Network Security, Deep Learning, Anomaly Detection, Classification Algorithms, Ensemble Methods, Threat Intelligence.

"EVALUATING THE EFFECTIVENESS OF MACHINE LEARNING MODELS IN CYBER ATTACK DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.10-15, November-2025, Available :http://www.jetir.org/papers/JETIRHD06002.pdf

"EVALUATING THE EFFECTIVENESS OF MACHINE LEARNING MODELS IN CYBER ATTACK DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. pp10-15, November-2025, Available at : http://www.jetir.org/papers/JETIRHD06002.pdf