원문정보
초록
영어
With varied and widespread attacks on information systems, intrusion detection systems (IDS) have become an indispensable part of security policy for protecting data. IDS monitor event logs and network traffic to uncover suspicious connections that deviate from the regular profile and identify them as threats or attacks. Like most of the cases the dataset used for intrusion detection i.e., KDD99 suffers two problems: imbalanced class distribution and curse of dimensionality. In this work SMOTE has been used for balancing the dataset and once balanced, Principal Component Analysis (PCA) has been used to extract the features. And after that on the transformed dataset Correlation based Feature Selection (CFS) is used to select a subset of important features. The reduced dimension dataset is tested with Support Vector Machines (SVM). Obtained results demonstrate improved detection accuracy, computational efficiency with minimal false alarms and less system resources utilization
목차
1. Introduction
2. Literature Survey
3. Techniques Used in Work
3.1. Support Vector Machine (SVM)
3.2. Principal Component Analysis
3.3. Correlation Based Feature Selection
3.4. Synthetic Minority Oversampling Technique(SMOTE)
4. Experimental Setup
5. Results and Discussions
6. Conclusion
References