• Vanitha J
• Dr. Raja Praveen

Nowadays, cybercrimes are increasing and have affected large organizations with highly sensitive information. Consequently, the affected organizations spent more resources analyzing the cybercrimes rather than detecting and preventing these crimes. Network forensics plays an important role in investigating cybercrimes; it helps organizations resolve cybercrimes as soon as possible without incurring a significant loss. This paper proposes a novel Proactive Approach to detect anomalies in network using Machine learning Technique. The proposed approach aims to use cybercrime evidence to reconstruct useful attack evidence. Moreover, it helps investigators to resolve cybercrime efficiently. In this paper, the dataset has been taken from real- time network intrusions in a military network environment. The proposed system provides a way to detect and classify multi class anomalies using Random Forest Classifier Algorithm. Random Forest has been selected since it can prevent intrusions up to a good extent by itself and can automatically improve accuracy on anomaly detection. Compared to the reactive approach carried out in network forensics, the results of the proposed machine learning approach prove to be more efficient in terms of time, cost and storage size.

PROACTIVE APPROACH BASED ANOMALY DETECTION IN NETWORK FORENSICS USING MACHINE LEARNING TECHNIQUE

"PROACTIVE APPROACH BASED ANOMALY DETECTION IN NETWORK FORENSICS USING MACHINE LEARNING TECHNIQUE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.f324-f332, May-2023, Available :http://www.jetir.org/papers/JETIR2305547.pdf

"PROACTIVE APPROACH BASED ANOMALY DETECTION IN NETWORK FORENSICS USING MACHINE LEARNING TECHNIQUE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppf324-f332, May-2023, Available at : http://www.jetir.org/papers/JETIR2305547.pdf