首页>
外国专利>
DEEP LEARNING-BASED MALICIOUS ATTACK DETECTION METHOD IN TRAFFIC CYBER PHYSICAL SYSTEM
DEEP LEARNING-BASED MALICIOUS ATTACK DETECTION METHOD IN TRAFFIC CYBER PHYSICAL SYSTEM
展开▼
机译：交通网络物理系统中基于深度学习的恶意攻击检测方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to a deep learning-based malicious attack detection method in a traffic cyber physical system. In the present invention, features of malicious data flows and normal data flows in behavior data of the traffic cyber physical system are extracted, and then original feature data is cleaned and encoded. Thereafter, the selection of the feature data is performed to obtain key features, and the key feature data is learned to establish a deep learning model. Finally, unknown behavior data that needs to be identified is inputted into the deep learning model, to identify whether the data is malicious data, so as to complete the malicious attack detection. The present invention uses the deep learning method to perform feature extraction and learning on program behaviors in the traffic cyber physical system, and detects a malicious attack according to a learning result, thereby effectively identifying a malicious attack in the traffic cyber physical system. The present invention can solve the problem that the traditional identification method is inaccurate and cannot identify an unknown malicious attack, nor implement the identification of a malicious attack in the traffic cyber physical system.
展开▼
