Cloud based Security Framework for Anomaly Based Intrusion Detection using Machine Learning Techniques

Cloud is one of the most recent trends in the domain of Computing. It enables the Service Providers to have an optimal usage of their Resources in order to gain more profit out of the available resources and computing capabilities. Since its inception, it had revolutionized the concept of Service Models as it is beneficial and cost friendly for both the Customers as well as Service Providers. But as said, every scientific discovery has its own benefits as well as adverse affects; the same is applicable to Cloud also. Now, due to easier implementation and large subscribers, the traffic on Cloud systems is increasing at an alarming rate, thereby providing opportunities for Hackers and other Unauthorized Users. There are various traditional approaches for implementing Intrusion Detection Systems but in this scenario, their performance will degrade significantly due to excessive Load, high Traffic, large number of Users and Resources. In this environment, an implementation of dynamic algorithm is desirable that can handle excessive load, high resource and user count. Such dynamic algorithm can be implemented in an optimal manner using Machine Learning techniques. Intrusion Detection Systems can be classified into various types, but the most common and implementable form is Anomaly based IDS. In such systems, the behaviour of the System parameters and stake holders is being observed on continuous basis. If an entity or a stake holder is behaving differently than its observed behaviour; it indicates that something went wrong. If this modified behaviour is continuous, then it means there has been an illegal activity being performed in the system. After this, the IDS take necessary actions to handle such an alarming situation. Developing an Anomaly based Intrusion Detection System using Machine Learning technique will be a suitable solution for developing a Security Framework for Cloud environment, so that the availability, fault tolerance, scalability and reliability of the Cloud environment should remain persistent, even in case of Fault or unauthorized access.

[1]  Gabriel Maciá-Fernández,et al.  Anomaly-based network intrusion detection: Techniques, systems and challenges , 2009, Comput. Secur..

[2]  Blessing Solomon B.C,et al.  Survey on Intrusion Detection System using Machine – Learning approaches , 2018 .

[3]  Ahmed Patel,et al.  An intrusion detection and prevention system in cloud computing: A systematic review , 2013, J. Netw. Comput. Appl..

[4]  Anazida Zainal,et al.  Intrusion Detection Techniques in Cloud Computing: A Review , 2018 .

[5]  Zouhair Chiba,et al.  New Anomaly Network Intrusion Detection System in Cloud Environment Based on Optimized Back Propagation Neural Network Using Improved Genetic Algorithm , 2019, Int. J. Commun. Networks Inf. Secur..

[6]  P. Mell,et al.  The NIST Definition of Cloud Computing , 2011 .

[7]  Karl Andersson,et al.  Performance Analysis of Anomaly Based Network Intrusion Detection Systems , 2018, 2018 IEEE 43rd Conference on Local Computer Networks Workshops (LCN Workshops).

[8]  V. R. Kolluru,et al.  Intrusion Detection System using AI and Machine Learning Algorithm , 2018 .

[9]  Mohammed Samaka,et al.  Machine Learning for Anomaly Detection and Categorization in Multi-Cloud Environments , 2017, 2017 IEEE 4th International Conference on Cyber Security and Cloud Computing (CSCloud).

[10]  Mahadevan Supramaniam,et al.  A Review of Intrusion Detection System using Machine Learning Approach , 2019 .

[11]  Dong Hyun Jeong,et al.  A survey of cloud-based network intrusion detection analysis , 2016, Human-centric Computing and Information Sciences.

[12]  Muttukrishnan Rajarajan,et al.  A novel framework for intrusion detection in cloud , 2012, SIN '12.

[13]  Pinal Patel,et al.  Comprehensive study on Machine Learning Techniques for IDS in Cloud Computing , 2014 .

[14]  Sabyasachi Patra,et al.  Machine Learning Approach for Intrusion Detection on Cloud Virtual Machines , 2013 .

[15]  Kiran.  ENHANCE DATA SECURITY IN CLOUD COMPUTING USING MACHINE LEARNING AND HYBRID CRYPTOGRAPHY TECHNIQUES , 2017 .

[16]  Ruth Breu,et al.  Anomaly Detection in the Cloud: Detecting Security Incidents via Machine Learning , 2012, EternalS@ECAI.

[17]  Kemal Hajdarevic,et al.  Survey on machine learning algorithms as cloud service for CIDPS , 2017, 2017 25th Telecommunication Forum (TELFOR).

[18]  Ram Shankar Siva Kumar,et al.  Practical Machine Learning for Cloud Intrusion Detection: Challenges and the Way Forward , 2017, AISec@CCS.

[19]  Miad Faezipour,et al.  Deep and Machine Learning Approaches for Anomaly-Based Intrusion Detection of Imbalanced Network Traffic , 2019, IEEE Sensors Letters.

[20]  Seema Joshi,et al.  Anomaly Detection and Categorization in Cloud Environment using Deep Learning Techniques , 2019 .

[21]  Rajiv Gandhi Salai,et al.  Virtual Host based Intrusion Detection System for Cloud , 2014 .