DT-LRoD: Decision Tree based Low-Rate Table Overflow Detection for SDN

DOI

10.2991/978-94-6463-740-3_28How to use a DOI?

Keywords

DT; LFTO; Low Rate; SDN

Abstract

Software-defined networking (SDN) transforms modern networks by enabling programmability for dynamic service provisioning. However, SDN faces significant challenges due to the limited capacity of flow tables in OpenFlow (OF) switches, which are typically stored in Ternary Content Addressable Memory (TCAM). This limitation makes SDN susceptible to attacks, particularly the Low-rate Flow Table Overflow (LFTO) attack. LFTO gradually fills the flow tables with malicious flows until it slowly degrades forwarding performance and corrupts network efficiency. This vulnerability is addressed by employing an attack detection framework that uses machine learning to detect LFTO attacks. A Decision Tree machine learning model structurally separates data into a tree using feature values as split criteria, each internal node representing a decision criterion, and each leaf node provides an outcome, providing transparency and excellent classification. The framework leverages the Decision Tree algorithm, which achieves a detection accuracy of 99.02%. Hence, the results from our experiments show that this approach to detecting LFTO attacks ensures uninterrupted data forwarding and preserves the availability of flow table resources in SDN.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pradyuman Kumar Verma
AU  - Surjit Singh
AU  - Ajay Kumar
PY  - 2025
DA  - 2025/06/25
TI  - DT-LRoD: Decision Tree based Low-Rate Table Overflow Detection for SDN
BT  - Proceedings of the 6th International Conference on Deep Learning, Artificial Intelligence and Robotics (ICDLAIR 2024)
PB  - Atlantis Press
SP  - 324
EP  - 333
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-740-3_28
DO  - 10.2991/978-94-6463-740-3_28
ID  - Verma2025
ER  -