Detecting anomalies in network traffic using maximum entropy estimation

By Yu Gu, Andrew McCallum, D. Towsley. ACM/SIGCOMM Internet Measurement Conference, 2005

430 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/bdd9dc7e771b3f940f833f58bdd6c217690f17f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Khaled Hamed Salah
2. Jawwad Ahmed Shamsi
3. Narmeen Zakaria Bawany
4. Stephen F. Gull
5. Tom Auld
6. Danda B. Rawat
7. Syed Ali Khayam
8. Junaid Khalid

In Computer Networks and Communications

1. Khaled Hamed Salah
2. Jawwad Ahmed Shamsi
3. Narmeen Zakaria Bawany
4. Stephen F. Gull
5. Tom Auld
6. Danda B. Rawat
7. Syed Ali Khayam
8. Junaid Khalid

In Control and Systems Engineering

1. Stephen F. Gull
2. Jawwad Ahmed Shamsi
3. Syed Ali Khayam
4. Khaled Hamed Salah
5. Junaid Khalid
6. Andrew William Moore
7. Tom Auld
8. Syed Akbar Mehdi

Citations in the corpus

• Revisiting Traffic Anomaly Detection Using Software Defined Networking (2011, methodology): “Similarly, the algorithms ported in this work [20,26,29,31] are simply proofs-of-concept to illustrate the flexibility and ease of anomaly detection algorithm implementation on an SDN platform.”
• Bayesian Neural Networks for Internet Traffic Classification (2007, positive): “[14], illustrate the application of machine-learning tech niques to the computation of baseline distributions representing traffi c behavior.”
• Entropy-based anomaly detection for in-vehicle networks (2011, neutral): “978-1-4577-0891-6/11/$26.00 ©2011 IEEE 1110”
• Software Defined Networking Architecture, Security and Energy Efficiency: A Survey (2017, background): “3) Maximum Entropy Detection [116] provides the operator with complete view of network from all dimensions.”
• DDoS Attack Detection and Mitigation Using SDN: Methods, Practices, and Solutions (2017, methodology): “Mehdi et al. [42] uses maximum entropy estimation [36] to estimate the benign traffic distribution to detect network security problems in home and office networks using SDN. Traffic is divided into packet classes and maximum entropy estimation is then used to develop a baseline benign distribution for…”