STUDY ON JUNIPER SMART SESSION ROUTER NETWORK TRAFFIC CHARACTERIZATION UTILIZING MACHINE LEARNING
Loading...
Authors
Thornton, Cory W.
Subjects
machine learning
VPN
Juniper Network
encrypted network traffic
network traffic
AI
characterization
tunneling traffic
packet capture
Smart Session Router
SSR
Secure Vector Routing
SVR
Virtual Private Network
VPN
Juniper Network
encrypted network traffic
network traffic
AI
characterization
tunneling traffic
packet capture
Smart Session Router
SSR
Secure Vector Routing
SVR
Virtual Private Network
Advisors
Barton, Armon C.
Date of Issue
2025-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
Virtual Private Networks (VPNs) provide secure communications through encryption and encapsulation mechanisms. Traditional VPNs, such as WireGuard, establish secure tunnels but rely on a stateless per-packet forwarding approach that lacks awareness of session continuity. Juniper Networks' Smart Session Router (SSR) introduces Session Vector Routing (SVR) as an alternative to conventional VPN routing. SVR ensures that bidirectional communication within a session follows the same path, improving network efficiency by reducing retransmissions, lowering overhead, and optimizing bandwidth. This study aims to investigate the classification of network traffic across both the SVR and a conventional VPN architecture and identify the optimal machine learning (ML) models and parameters for encrypted traffic protocol and payload classification. To achieve this classification, we will collect a novel dataset by establishing both SVR and VPN connections in a lab setting, generating network traffic across both network architectures, and capturing packet data flows via packet analysis tools. The captured traffic will be analyzed to determine its classification feasibility based on application-level protocols and payload flow characteristics. Several ML models will be trained and evaluated to identify the most effective methods for traffic classification and the features that most contribute to each model.
Type
Thesis
Description
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
Funding
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.