• NANDURI MANIKANTA SWAMY
• MOHAMMAD RAQUIB ALI
• MOHAMMAD AMEER AMANULLA KHAN
• PITTA VAMSI
• PHANI BABU KOMARAPU

In today's rapidly evolving digital environment, cybersecurity risks pose significant challenges for network managers. Traditional anomaly detection tools often struggle to detect advanced network threats due to the increasing complexity and subtlety of modern attacks. This paper proposes a novel hybrid anomaly detection framework, combining a Deep Neural Network (DNN) for supervised classification with the Isolation Forest method for unsupervised detection. By integrating these approaches, the system aims to enhance detection accuracy, reduce false positives, and provide scalable real-time monitoring. Experimental results demonstrate substantial improvements in detection rates and operational efficiency compared to existing methods.

Anomaly Detection, Network Security, Hybrid Model, Isolation Forest, Deep Neural Network, Cybersecurity, Machine Learning, Real-Time Processing.

"ANOMALY DETECTION IN NETWORK TRAFFIC: A HYBRID APPROACH USING ISOLATION FOREST AND DEEP NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.i98-i104, March-2025, Available :http://www.jetir.org/papers/JETIR2503813.pdf

"ANOMALY DETECTION IN NETWORK TRAFFIC: A HYBRID APPROACH USING ISOLATION FOREST AND DEEP NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppi98-i104, March-2025, Available at : http://www.jetir.org/papers/JETIR2503813.pdf