Efficient In-Network Traffic Classification Using Programmable Switches With AdaFlow
- 8 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 22 (6) , 5532-5549
Abstract
In-network ML-based traffic classification using programmable switches has enabled faster decisions and reduced the cost of the security infrastructure and management overheads. However, due to constraints on per-packet operations and limited stateful memory in the switch data plane, there is a fundamental tradeoff between traffic classification accuracy and switch memory requirements. Existing works fall short of accurately classifying traffic with diverse flow characteristics while keeping the memory footprint low. In this paper, we propose AdaFlow, a system that aims to address this gap by incorporating traffic-specific heuristics while designing the in-network classifier. We evaluate the AdaFlow prototype via simulations and also on a testbed with an Intel Barefoot Tofino switch. Compared to the state-of-the-art, AdaFlow improves accuracy up to 7% for various use-cases while keeping the memory overheads similar to or lower than those of the existing systems.Keywords
Funding Information
- National Security Council Secretariat (NSCS) and ZF Technologies, India
This publication has 42 references indexed in Scilit:
- Network anomaly detection methods in IoT environments via deep learning: A Fair comparison of performance and robustnessComputers & Security, 2023
- A Learning Methodology for Line-Rate Ransomware Mitigation with P4 Switches2022
- INC: In-Network Classification of Botnet Propagation at Line Rate2022
- Machine-Learning-Enabled DDoS Attacks Detection in P4 Programmable NetworksJournal of Network and Systems Management, 2021
- SwitchTree: in-network computing and traffic analyses with Random ForestsNeural Computing and Applications, 2020
- TON_IoT Telemetry Dataset: A New Generation Dataset of IoT and IIoT for Data-Driven Intrusion Detection SystemsIEEE Access, 2020
- Intel Tofino2 – A 12.9Tbps P4-Programmable Ethernet Switch2020
- Developing Realistic Distributed Denial of Service (DDoS) Attack Dataset and Taxonomy2019
- PeerRush: Mining for unwanted P2P trafficJournal of Information Security and Applications, 2014
- Gene Selection for Cancer Classification using Support Vector MachinesMachine Learning, 2002