No abstract

Today, cloud computing has become popular among users in organizations and companies. Security and efficiency are the two major issues facing cloud service providers and their customers. Since cloud computing is a virtual pool of resources provided in an open environment (Internet), cloud-based services entail security risks. Detection of intrusions and attacks through unauthorized users is one of the biggest challenges for both cloud service providers and cloud users. In the present study, artificial intelligence techniques, e.g. MLP Neural Network sand particle swarm optimization algorithm, were used to detect intrusion and attacks. The methods were tested for NSL-KDD, KDD-CUP datasets. The results showed improved accuracy in detecting attacks and intrusions by unauthorized users. Keywords:Cloud Security; Intrusion Detection; Neural Networks; Particle Swarm Optimization. Article History:Received: 18 September 2017 Accepted: 15 December 2017 1-IntroductionUploading sensitive data to public cloud storage services poses security risks such as accessibility, confidentiality and integration to organizations. Moreover, non-stop cloud services have caused high levels of intrusion and abuse. Using firewall and intrusion detection system is the only permanent solution to protect users' data and cloud resources. Some of attacks, like DOS, are too complex for firewalls; so, one can use attack detection methods with the ability to detect various types of attacks. Recently, intelligent and meta-heuristic algorithms are the most commonly used attack detection techniques. Meta-heuristic algorithms can be used either to analyse attack database or to optimize and increase the accuracy of the classifiers. Therefore, these methods are reliable and suitable to detect attacks and anomalies. In this study, MLP was used to classify attacks and then Particle Swarm algorithm was employed to optimize and increase the accuracy of this classifier. Section 2 presents the literature review. Positioning of the proposed system in a network is determined in section 3. Section 4 explains the tools used in the proposed system. Structure of the proposed method is presented in section 5. In section 6, the proposed system is tested using KDD cup and NSL-KDD databases. Finally, section 7 presents our conclusions. 2-Literature ReviewLi et al (2012) proposed a neural network based IDS which was a distributed system with an adaptive architecture so as to make full use of the available resources without overloading any single machine in the cloud. In addition, with the machine learning ability from neural network, the proposed IDS can detect newer types of attacks with fairly accurate results. Evaluation of the proposed IDS with the KDD dataset on a physical cloud platform shows that it is a promising approach to detect attacks in cloud infrastructure. The method reached diagnostic accuracy of 99% for the KDD dataset [5]. Kannan et al (2012) introduced a new intrusion detection system using Genetic Algorithm for feature selection and Fuzzy Sup...

No abstract

No abstract

No abstract