International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 13 Issue: 02 | Feb 2026
p-ISSN: 2395-0072
www.irjet.net
A REVIEW OF SPLIT LEARNING–BASED SECURE TRAFFIC CLASSIFICATION FOR PRIVACY-SENSITIVE NETWORKS Annapurna Yadav1, Mrs. Arifa Khan2 1Master of Technology, Computer Science and Engineering, Lucknow Institute of Technology, Lucknow, India 2Assistant Professor, Department of Computer Science and Engineering, Lucknow Institute of Technology,
Lucknow, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The rapid proliferation of encrypted
distributed learning paradigms—particularly split learning—have emerged as promising solutions. This review examines the evolution, challenges, and emerging role of split learning in secure traffic classification for privacysensitive networks.
communication and data-driven network services has significantly increased the demand for accurate and privacypreserving traffic classification mechanisms. Traditional traffic analysis techniques, including deep packet inspection and centralized machine learning models, often require access to raw packet payloads, raising serious privacy, regulatory, and security concerns in privacy-sensitive environments such as healthcare, finance, and critical infrastructure networks. Recently, split learning has emerged as a promising distributed learning paradigm that partitions deep neural networks between clients and servers, enabling collaborative model training without direct sharing of raw data. This review systematically examines the state-of-the-art research on split learning–based secure traffic classification, focusing on architectural designs, privacy guarantees, communication overhead, and performance trade-offs. We analyze how split learning compares with related paradigms such as federated learning and differential privacy–based methods in the context of encrypted and large-scale network traffic. Furthermore, this review synthesizes existing datasets, evaluation metrics, and threat models adopted in prior studies, identifying limitations in benchmarking practices and security analysis. Key challenges, including gradient leakage, scalability constraints, and adversarial robustness, are critically discussed. Finally, potential research directions are outlined to guide future developments toward practical, secure, and high-performance deployment of split learning frameworks for traffic classification in privacy-sensitive networks.
1.1 Background and Problem Context 1.1.1 Evolution of Network Traffic Classification Network traffic classification has evolved through several methodological paradigms. Early approaches relied on portbased identification, where traffic flows were categorized based on well-known transport layer port numbers. While computationally efficient, this technique became unreliable as applications increasingly adopted dynamic ports and port obfuscation mechanisms (Moore and Papagiannaki, 2005). Subsequently, deep packet inspection (DPI) techniques were introduced, enabling payload-level inspection to achieve fine-grained classification. DPI significantly improved accuracy but required direct access to packet content, raising scalability and privacy concerns (Nguyen and Armitage, 2008). With the proliferation of encrypted and high-volume traffic, statistical and machine learning-based methods gained prominence. These approaches leveraged flow-level features such as packet inter-arrival time, flow duration, and byte distribution patterns. More recently, deep learning architectures—including convolutional neural networks (CNNs) and recurrent neural networks (RNNs)—have demonstrated superior performance in encrypted traffic classification tasks by automatically extracting discriminative features (Lotfollahi et al., 2020).
Key Words: Split Learning, Secure Traffic Classification, Privacy-Preserving Machine Learning, Encrypted Network Traffic, Federated Learning, Network Security, Distributed Deep Learning
1. INTRODUCTION
1.1.2 Rise of Encrypted Traffic and Privacy Regulations
The exponential growth of Internet-enabled services, cloud computing, IoT ecosystems, and mobile applications has intensified the need for efficient and intelligent network traffic classification. Traffic classification plays a fundamental role in network management, intrusion detection, quality-of-service (QoS) enforcement, and cybersecurity operations. However, the increasing deployment of encryption protocols and strict privacy regulations has significantly complicated traditional traffic analysis approaches. In this context, privacy-preserving
© 2026, IRJET
|
Impact Factor value: 8.315
The widespread adoption of encryption protocols such as TLS has fundamentally altered the traffic classification landscape. Current reports indicate that a substantial majority of Internet traffic is encrypted, limiting visibility into packet payloads and rendering DPI ineffective (Anderson et al., 2017). Simultaneously, regulatory frameworks such as the General Data Protection Regulation (GDPR) and sector-specific compliance mandates have imposed strict requirements on
|
ISO 9001:2008 Certified Journal
|
Page 746