Detecting Network Intrusion based on Machine Learning Algorithms

	International Journal of P2P Network Trends and Technology (IJPTT)
	© 2020 by IJPTT Journal
	Volume-10 Issue-3
	Year of Publication : 2020
	Authors : S.Kavitha, D.Subiksha, J.Aarthi, M.Priyanga, M.Malathi

Citation

MLA Style:S.Kavitha, D.Subiksha, J.Aarthi, M.Priyanga, M.Malathi "Detecting Network Intrusion based on Machine Learning Algorithms" International Journal of P2P Network Trends and Technology 10.3 (2020): 1-5.

APA Style:S.Kavitha, D.Subiksha, J.Aarthi, M.Priyanga, M.Malathi(2019). Detecting Network Intrusion based on Machine Learning Algorithms. International Journal of P2P Network Trends and Technology, 10(3),1-5.

Abstract

An IDS is a hardware or software application that monitors network traffic data on a system or a network .To provide security for network only firewall and antivirus is not sufficient so, there is need to give more security to the network so, Intrusion Detection System is used. DDoS defense mechanism named CoFence which facilitates a domain-helps-domain collaboration network among NFV-based domain networks. CoFence through resource sharing helps to handle large volume of DDoS attacks. Specifically, it designs a dynamic resource allocation mechanism for domains so that the resource allocation is fair, efficient, and incentive compatible.Current Static Detection Techniques only detect the known malicious attacks, but it also intends to provide the NIDS the capability to analyse and classify the malicious contents along with the accuracy. Honeypot is used to detect intruders and to identify all the malicious activities performed over the internet. Naïve Bayes algorithm is used for classification of the data into normal and abnormal activities along with the accuracy.

References

[1] Aditya Phadke et.al proposed, “A Review of Machine Learning Methodologies for Network Intrusion Detection “in 2019.
[2] Bahman Rashidi and Carol Fung proposed, “A Collaborative DDoS Defence Using Network Function Virtualization “ in 2016
[3] Iman Sharafaldin, Arash Habibi Lashkari and Ali A. Ghorbani proposed, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization” in 2018
[4] Jayshree Jha and Leena Ragh proposed, “Intrusion Detection System using Support Vector Machine” in 2013.
[5] K. Swathi , D. Sree Lakshmi proposed, “Network Intrusion Detection Using Fast k-Nearest Neighbour Classifier” in 2014.
[6] P. Ransack, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, “Group lens: An open architecture for collaborative filtering of Netnews,” in Proc CSCW, 1994, pp. 175–186.
[7] Md Nasimuzzaman Chowdhury & Ken Ferens, Mike Ferens (2016). “Network Intrusion Detection Using Machine Learning”.2016 Int?l Conf. Security and Management, SAM?16.
[8] Eslamnezhad, Mohsen & Varjani, A. (2014). “Intrusion detection based on Min Max K-means clustering”. 2014 7th International Symposiumon Telecommunications, IST 2014. 804-808.
[9] http://www.statsoft.com/textbook/support-vectormachines/.
[10] C.J.Fung and B. McCormick. Vguard: A distributed denial of service attack mitigation method using network function virtualization. In Network and Service Management (CNSM), 2015 11th International Conference on, pages 64– 70. IEEE, 2015.
[11] Arborddos detection and protection. http://security.arbornetworks.com/protection/?gc lid=CNrToYHYqM0CFRY7gQodjvcN_w.
[12] Atlas q2 2015 update. http://www.slideshare.net/Arbor Networks/atlas-q2- 2015final.
[13] Biggest internet attack in history threatens critical systems. http://www.ibtimes.co.uk/biggest-internet-attack-historythreatens- critical-infrastructure-450969.
[14] Ghosal, Amrita & Halder, Subir. (2017).“A survey on energy efficient intrusion detection in wireless sensor networks”. Journal of Ambient Intelligenceand Smart Environments. 9. 239-261. 10.3233/AIS-170426.
[15] Arthur, David & Vassilvitskii, Sergei. (2007). “K-Means++: The Advantages of Careful Seeding”. Proc. of the Annu. ACM-SIAM Symp. on Discrete Algorithms.

Keywords
DDoS Attack, Network Function Virtualization (NFV), Network intrusion detection systems; Machine learning.