Research Article
Research on Host Intrusion Detection Method Based on Big Data Technology
@INPROCEEDINGS{10.1007/978-3-030-67871-5_39, author={Lei Ma and Hong-xue Yang}, title={Research on Host Intrusion Detection Method Based on Big Data Technology}, proceedings={Advanced Hybrid Information Processing. 4th EAI International Conference, ADHIP 2020, Binzhou, China, September 26-27, 2020, Proceedings, Part I}, proceedings_a={ADHIP}, year={2021}, month={2}, keywords={Big data technology Intrusion behavior Outlier probability Detection accuracy}, doi={10.1007/978-3-030-67871-5_39} }- Lei Ma
Hong-xue Yang
Year: 2021
Research on Host Intrusion Detection Method Based on Big Data Technology
ADHIP
Springer
DOI: 10.1007/978-3-030-67871-5_39
Abstract
When the host runs a large number of applications at the same time under normal activities, the abnormal probability value of the host after the fusion of evidence is large, resulting in false alarms, resulting in a reduction in the final detection accuracy of the detection method. A host intrusion detection method based on big data technology. Using big data processing intrusion detection index weight, sliding window is introduced. According to the number of times of host resource availability anomaly in the time window, the value of anomaly probability is controlled, the index anomaly closed value is determined, and the availability anomaly threshold is set to realize host intrusion detection. The experiment builds a data collection platform and compares the two traditional detection methods with the detection methods studied in the paper. The results show that the detection accuracy of the proposed detection method is about 98%, and the detection of host intrusion behavior is more accurate and the detection time is shortened.
