Abstract
Traffic classification (TC) has a principal function in autonomous network management. Recently, deep learning and machine learning-based TC have become popular than the traditional port-based and protocol-based TC due to practices such as port disguise and payload encryption. The flow-based TC is reliable as it relies on time-related statistical features. Federated learning is a distributed machine learning technique to train improvised deep/machine learning models with less privacy distress. The organizations or enterprises having similar business models may take participation in building a federated model for their network traffic characterization. In this study, we build a cross-silo horizontal federated model for TC using flow-based time-related features. The federated model shows comparable performance to the centralized model.
| Original language | English |
|---|---|
| Title of host publication | APNOMS 2020 - 2020 21st Asia-Pacific Network Operations and Management Symposium |
| Subtitle of host publication | Towards Service and Networking Intelligence for Humanity |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 389-392 |
| Number of pages | 4 |
| ISBN (Electronic) | 9788995004388 |
| DOIs | |
| Publication status | Published - Sept 2020 |
| Event | 21st Asia-Pacific Network Operations and Management Symposium, APNOMS 2020 - Daegu, Korea, Republic of Duration: 22 Sept 2020 → 25 Sept 2020 |
Publication series
| Name | APNOMS 2020 - 2020 21st Asia-Pacific Network Operations and Management Symposium: Towards Service and Networking Intelligence for Humanity |
|---|
Conference
| Conference | 21st Asia-Pacific Network Operations and Management Symposium, APNOMS 2020 |
|---|---|
| Country/Territory | Korea, Republic of |
| City | Daegu |
| Period | 22/09/20 → 25/09/20 |
Bibliographical note
Publisher Copyright:© 2020 KICS.
Keywords
- Cross-silo
- Horizontal federated learning
- Ten-sorflow federated
- Traffic classification