• Gayathri R
• Dhivya S
• BanuPriya M

Identifying unauthorized users becomes challenging when individuals employ tools like anonymizing proxies or Virtual Private Networks (VPNs) to conceal their identity. This study introduces computational models aimed at overcoming the current limitations in detecting VPN-related activities. The developed model utilizes machine learning algorithms trained on flow statistics data extracted from the Transmission Control Protocol (TCP) header in captured network packets. Through validation testing, the presented models demonstrate a robust ability to classify network traffic into two categories: direct (originating directly from a user's device) or indirect (utilizing VPNs for identity and location concealment) with a high level of accuracy.

Transmission control protocol, Random Forest, Random Logistic, Machine learning.

"detection of virtual private network using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.f558-f566, April-2024, Available :http://www.jetir.org/papers/JETIR2404560.pdf

"detection of virtual private network using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppf558-f566, April-2024, Available at : http://www.jetir.org/papers/JETIR2404560.pdf