Intrusion Detection Model Based on SAE and BALSTM

To solve the problems of low detection accuracy, high false positive rate and unbalanced network data sets in the high-dimensional massive data environment of traditional intrusion detection model, an intrusion detection model based on improved Stack autoencoder (SAE) and bidirectional feature atten...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) s. 1192 - 1197
Hlavní autoři: Jiajia, Fan, Jiangfeng, Xu, Junfeng, Zhang
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 28.06.2021
Témata:
Attention mechanism
Bidirectional short-time memory network
Computational modeling
Computer applications
Conferences
Feature extraction
Improved stack autoencoder
Intrusion detection
Simulation
Smote-Tomek
Standardization
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To solve the problems of low detection accuracy, high false positive rate and unbalanced network data sets in the high-dimensional massive data environment of traditional intrusion detection model, an intrusion detection model based on improved Stack autoencoder (SAE) and bidirectional feature attention short-time memory network (BALSTM) is proposed. In the model, firstly, Smote-Tomek combined sampling algorithm is used to reduce the imbalance rate of data sets, and then batch standardization and early stop mechanism are used to improve SAE for feature extraction, which accelerates the convergence speed of the model and solves the over-fitting problem. Finally, an attention module is added to BLSTM, which enables BALSTM model to pay attention to context information and strengthen the learning of important features. Analysis and simulation results show that the model has better performance in accuracy and false alarm rate.
DOI:10.1109/ICAICA52286.2021.9498102