Nor Dzuhairah Hani, Jamaludin (2019) Intrusion detection systems using K-means clustering system. Faculty of Computer System & Software Engineering, Universiti Malaysia Pahang.
|
Pdf
Intrusion detection systems using K-means clustering.pdf - Accepted Version Download (816kB) | Preview |
Abstract
Internet is the biggest platform for people all over the world to connect with each other, and to search for important information and such. Along with the raising of internet usage, the number of cases of intrusion attacks also increases. Because of this, intrusion detection is important, especially for large companies which held huge and confidential data and information. This system works to detect the abnormal connection of a network so that a stronger protection could be build. Since the attack is not restricted into only one type, a data mining technique is applied to classify all types of attack from a huge amount of data entering into a network. By using this technique, the intrusion detection system could work better. In this research, data mining technique of K-means clustering system are used to detect the intrusion and attack. 1999 KDD Cup Dataset is used for training, testing, and validation of the system. The dataset is famous among intrusion detection system researcher for its data which resembles real attacks at real times.
| Item Type: | Undergraduates Project Papers |
|---|---|
| Additional Information: | Project Paper (Bachelors of Computer Science (Software Engineering)) -- Universiti Malaysia Pahang – 2019, SV: ENCIK MOHD HAFIZ BIN MOHD HASSIN, e-Thesis |
| Uncontrolled Keywords: | Intrusion attacks; intrusion detection; data mining |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software |
| Faculty/Division: | Faculty of Computer System And Software Engineering |
| Depositing User: | Mrs. Sufarini Mohd Sudin |
| Date Deposited: | 27 Nov 2019 08:39 |
| Last Modified: | 27 Nov 2019 08:39 |
| URI: | http://umpir.ump.edu.my/id/eprint/26636 |
| Download Statistic: | View Download Statistics |
Actions (login required)
 |
View Item |