Research Article
An Adaptive Algorithm Based on Adaboost for Mimicry Multimode Decisions
@INPROCEEDINGS{10.1007/978-3-030-72792-5_12, author={Feng Wang and Dingde Jiang and Zhihao Wang and Yingchun Chen}, title={An Adaptive Algorithm Based on Adaboost for Mimicry Multimode Decisions}, proceedings={Simulation Tools and Techniques. 12th EAI International Conference, SIMUtools 2020, Guiyang, China, August 28-29, 2020, Proceedings, Part I}, proceedings_a={SIMUTOOLS}, year={2021}, month={4}, keywords={Information security Mimicry multimode decision Heterogeneous executor Adaboost}, doi={10.1007/978-3-030-72792-5_12} }- Feng Wang
Dingde Jiang
Zhihao Wang
Yingchun Chen
Year: 2021
An Adaptive Algorithm Based on Adaboost for Mimicry Multimode Decisions
SIMUTOOLS
Springer
DOI: 10.1007/978-3-030-72792-5_12
Abstract
The traditional information security protection cannot prevent the malicious and directed intrusion of the network. To discover potential risks comprehensively, accurately, and timely, the polymorphic heterogeneous executor is constructed to confuse the attacker, called mimicry multimode decision. However, heterogeneous executors are composed of complex hardware, systems and applications, so how to select the optimal combination to face the potential risks becomes a problem. This paper proposes a mimicry multimode decision scheme based on Adaboost machine learning algorithm. The administrator can utilize Adaboost classifier to adaptively select the combination of the most defensible executor, so as to realize mimicry multimode defense and improve the security of applications. Simulation results demonstrate that the adaptive mimicry multimode decision method is promising.
