14 research outputs found
Adaptive Learning and Automatic Filtering of Distributed Denial of Service (DDoS) Attacks in Cloud Computing Environment
No full text
Recursive Percentage based Hybrid Pattern Training for Supervised Learning
No full textSupervised learning algorithms, often used to find the I/O relationship in data, have the tendency to be trapped in local optima as opposed to the desirable global optima. In this paper, we discuss the RPHP learning algorithm. The algorithm uses Real Coded Genetic Algorithm based global and local searches to find a set of pseudo global optimal solutions. Each pseudo global optimum is a local optimal solution from the point of view of all the patterns but globally optimal from the point of view of a subset of patterns. Together with RPHP, a Kth nearest neighbor algorithm is used as a second level pattern distributor to solve a test pattern. We also show theoretically the condition under which finding several pseudo global optimal solutions requires a shorter training time than finding a single global optimal solution. As the difficulty of curve fitting problems is easily estimated, we verify the capability of the RPHP algorithm against them and compare the RPHP algorithm with three counterparts to show the benefits of hybrid learning and active recursive subset selection. The RPHP shows a clear superiority in performance. We conclude our paper by identifying possible loopholes in the RPHP algorithm and proposing possible solutions
An impact analysis: Real time DDoS attack detection and mitigation using machine learning
No full textA Survey of Security Models Using Effective Moving Target Defenses
No full textThis article describes how nowadays, attackers are targeting valuable assets and infrastructures in networked systems causing an impact on enterprises and individuals. By implementing moving target defenses helps to prevent cyber-attacks by changing the attack surface. Some security models like Attack Graph (A.G) and Attack Tree (A.T) provide a formal method to access and compare the effectiveness of them. So, in this article, the authors incorporate moving target defenses in a security model, using a Hierarchical Attack Representation Model (HARM), to compare and access the effectiveness of the security. In addition, the authors are also taking important measures (IMs) for implementing MTD techniques to enhance the scalability of the network. Finally, they compare the scalability of an attack graph and HARM models by implementing MTD techniques to find the effectiveness of security in network.</jats:p
Combat model-based DDoS detection and defence using experimental testbed: a quantitative approach
No full text
