Abstract | ||
---|---|---|
A robust Network Intrusion Detection System (NIDS) has become the need of today's era. To provide a robust mechanism require to distinguish between normal and anomalous activities, outliers detection with the help of data mining, play an important role in detection and distinction of such activities in the midst of enhanced performance in detection of false alarm. Now day's researchers focus on applying outlier detection techniques for anomaly detection because of its promising results in discover true attacks and in sinking false alarm rate. So this paper contributed a enhanced mechanism of outlier detection to enhance accuracy in intrusion detection by introducing Density based Outlier detection into Data Mining using Hamming Densities of a data point. Hamming density is k-nearest neighbour divided by Hamming-distance. Analyzed the outcomes of our proposed by doing experiment using UCI repository KDD Cup' 99 Intrusion data-set on our simulator work and compare the result with other such existing algorithms like LOF, LOF' and found more accuracy and increase in detecting the number of true positive alarm in our proposed work. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-60618-7_26 | SoCPaR |
Keywords | Field | DocType |
Hamming distance,Outlier,NIDS,Attack,Density based | Anomaly detection,Hamming code,False alarm,Pattern recognition,Computer science,Outlier,Anomaly-based intrusion detection system,Hamming distance,Artificial intelligence,Constant false alarm rate,Intrusion detection system | Conference |
Volume | ISSN | Citations |
614 | 2194-5357 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Neeraj Kumar | 1 | 0 | 0.34 |
Upendra Kumar | 2 | 4 | 4.84 |