Security against ARP Spoofing Attacks using Bayesian Support Vector Regression
C. Divya1, D Francis Xavier Christopher2
1C. Divya, Research Scholar, School of Computer Studies, Rathnavel Subramaniam College of Arts and Science, Coimbatore, Tamilnadu.
2Dr D Francis Xavier Christopher, Director, School of Computer Studies, Rathnavel Subramaniam College of Arts and Science, Coimbatore, Tamilnadu
Manuscript received on 05 May 2019 | Revised Manuscript received on 12 May 2019 | Manuscript published on 30 May 2019 | PP: 636-644 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5496058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: TIn computer networks, Address Resolution Protocol (ARP) discovers the MAC address associated with an IP address but ARP lacks authentication in exchanging MAC address between hosts. This creates opportunity for hackers to employ ARP spoofing to damage the data and system. Many protection systems have been developed but the requirement to modify the basic network structure and expensive tools make it difficult to utilize. This paper investigates the practical limitations and considers the problem of detecting incompletely rectified adversaries from past sessions. For resolving this problem, Bayesian Support Vector Regression based ARP (BSVR-ARP) spoofing attacks protection mechanism is proposed. This mechanism considers the host configuration changes and network transmission errors for a probability prediction algorithm to detect the attackers. The attackers from the past sessions are also detected based on past knowledge and then using these detection results, they are either rectified or discarded from the network transmission routes. The detection and prevention of ARP spoofing has been accurate and effective in BSVR-ARP. The experimental results show that the proposed mechanism overcomes the limitations of other ARP spoofing prevention schemes and has higher accuracy of detection with minimal errors.
Keyword: Address Resolution Protocol, ARP Spoofing, Cache Poisoning, Bayesian Support Vector Regression, probability prediction algorithm
Scope of the Article: Support Vector