Gulay Oke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gulay Oke has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- George Loukas
University of Greenwich
2 shared publications - Erol Gelenbe
Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Gliwice, Poland
1 shared publication
Latest Publications
- Open Access
- 1 January 2008
- Published by BCS Learning & Development Ltd in Electronic Workshops in Computing
Distributed Defence Against Denial of Service Attacks: A Practical View
In recent years, Denial of Service attacks have evolved into a predominant network security threat. In our previous work, we identified the necessary building blocks for an effective defence mechanism and suggested ways to integrate them. Here, we present the results of this integration on the DoS-resilience of a real networking testbed which runs the Self-Aware CPN routing protocol. The incoming traffic at each node is monitored with a detection mechanism that is based on maximum likelihood estimation. In response to high probability of attack, the traffic is ratelimited proportionally to the measured probability. We illustrate the results of the experiments we have performed to demonstrate the efficiency of the distributed defence system that we propose.
- 1 January 2008
- Published by BCS Learning & Development Ltd in Electronic Workshops in Computing
Open AccessDistributed Defence Against Denial of Service Attacks: A Practical View
In recent years, Denial of Service attacks have evolved into a predominant network security threat. In our previous work, we identified the necessary building blocks for an effective defence mechanism and suggested ways to integrate them. Here, we present the results of this integration on the DoS-resilience of a real networking testbed which runs the Self-Aware CPN routing protocol. The incoming traffic at each node is monitored with a detection mechanism that is based on maximum likelihood estimation. In response to high probability of attack, the traffic is ratelimited proportionally to the measured probability. We illustrate the results of the experiments we have performed to demonstrate the efficiency of the distributed defence system that we propose.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10987584,p. 1-6
Detecting Denial of Service Attacks with Bayesian Classifiers and the Random Neural Network
Denial of service (DoS) is a prevalent threat in today's networks. While such an attack is not difficult to launch, defending a network resource against it is disproportionately difficult, and despite the extensive research in recent years, DoS attacks continue to harm. The first goal of any protection scheme against DoS is the detection of its existence, ideally long before the destructive traffic build-up. In this paper we propose a generic approach which uses multiple Bayesian classifiers, and we present and compare four different implementations of it, combining likelihood estimation and the random neural network (RNN). The RNNs are biologically inspired structures which represent the true functioning of a biophysical neural network, where the signals travel as spikes rather than analog signals. We use such an RNN structure to fuse real-time networking statistical data and distinguish between normal and attack traffic during a DoS attack. We present experimental results obtained for different traffic data in a large networking testbed.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10987584,p. 1-6
Detecting Denial of Service Attacks with Bayesian Classifiers and the Random Neural Network
Denial of service (DoS) is a prevalent threat in today's networks. While such an attack is not difficult to launch, defending a network resource against it is disproportionately difficult, and despite the extensive research in recent years, DoS attacks continue to harm. The first goal of any protection scheme against DoS is the detection of its existence, ideally long before the destructive traffic build-up. In this paper we propose a generic approach which uses multiple Bayesian classifiers, and we present and compare four different implementations of it, combining likelihood estimation and the random neural network (RNN). The RNNs are biologically inspired structures which represent the true functioning of a biophysical neural network, where the signals travel as spikes rather than analog signals. We use such an RNN structure to fuse real-time networking statistical data and distinguish between normal and attack traffic during a DoS attack. We present experimental results obtained for different traffic data in a large networking testbed.