Abstract
Due to using the single classification algorithm can not meet the performance requirements of intrusion detection, combined with the numerical value of KNN and the advantage of naive Bayes in the structure of data, an intrusion detection model KNN-NB based on KNN and Naive Bayes hybrid classification algorithm is proposed. The model first preprocesses the NSL-KDD intrusion detection data set. And then by exploiting the advantages of KNN algorithm in data values, the model calculates the distance between the samples according to the feature items and selects the K sample data with the smallest distance. Finally, by naive Bayes to get the final result. The experimental results on the NSL-KDD dataset show that the KNN-NB algorithm can meet the requirement of balanced performance than the traditional KNN and Naive Bayes algorithm in term of accuracy, sensitivity, false detection rate, specificity, and missed detection rate.
Highlights
At present, intrusion detection technology can be divided into two categories: anomaly detection and misuse detection[1]
Based on the above problems, this paper proposes a hybrid classification algorithm KNN-NB based on KNN and Naive Bayes
This paper proposes an intrusion detection model based on KNN and Naive Bayes hybrid classification algorithm
Summary
Intrusion detection technology can be divided into two categories: anomaly detection and misuse detection[1]. Kulariya M et al used KNN algorithm to perform intrusion detection and the experimental results show that the KNN algorithm when doing intrusion detection has high accuracy and specificity and efficiency, but its false alarm rate and missed detection rate are high and the sensitivity is low[4]. This will cause many abnormal behaviors to be detected without harming the system or a lot of normal. The experimental results on the NSLKDD data set show that the KNN-NB algorithm can meet the performance equalization requirements in terms of accuracy, sensitivity, error rate, specificity and missing rate, etc., compared with traditional KNN and naive Bayesian algorithms.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
