Detecting DDoS Attacks in Programmable Data Planes

Detecting DDoS Attacks in Programmable Data Planes

Building a machine learning model using data plane programming language such as P4 that detect network security attacks at line rate with high accuracy

Recent breakthroughs in the field of programmable networks have allowed for further programmability of switches. As opposed to fixed-function switches, programmable switches allow researchers to propose and evaluate new ideas in sufficiently realistic settings. In this project, we perform in-network analysis of the network data by exploiting the power of programmable data plane. As such, performing the detection of DDoS attacks in programmable data planes is a promising alternative to traditional approaches.


Developing a lightweight machine learning model and embed it into a programmable switch to accurately detect DDoS attacks flows at line rate.

Learning outcome

  • Learning switches programming language such as P4
  • Application of AI in a networking context
  • Excellent opportunities to publish your research results in the form of a scientific publication


  • Interested in networking and security
  • Interested in machine learning
  • Preferable knowledge of python


  • Azza Hassan Mohamed Ahmed

Collaboration partners

  • University of Gloucestershire, UK

Associated contacts

Azza Hassan Mohamed Ahmed

Postdoctoral Fellow