An IoT Intrusion Detection Method for Digital Campus Network Based on Feature Fusion of Offset Data in Multi-source Domain
Currently conventional intrusion detection methods for digital campus networks mainly batch process the data by constructing a autoencoder and construct a detection criterion by learning the data features of malicious attacks,which leads to poor detection accuracy due to neglecting the offsets of different data sources.In this re-gard,An IoT intrusion detection method for digital campus network based on feature fusion of offset data in multi-source domain was proposed.Firstly,the feature dimension was judged,so as to clarify the type of data that can be extracted.Then by constructing the offset coefficient correction index,the offset data from multi-source domain was fused and processed,and the optimization iteration was used to optimize the feature parameters at different lev-els.Finally,the feature offset criteria are extracted,and the fused feature vectors were compared with the offset criteria to realize the effective judgment of the intrusion data.The experimental results show that,the proposed method has higher detection accuracy and better detection effect detection effect.
NETL
NSTL
万方数据
