Security Detection Design for Laboratory Networks Based on Enhanced LSTM and AdamW Algorithms

Abstract

With the addition of multimedia big data, the diversification of network data types becomes more prominent, the proportion of unstructured data increases sharply, and the requirements of data application show the characteristics of rapid change. Laboratory servers hold a large amount of core experimental data, which is at risk of being compromised in the event of a cyberattack, and the rapid pace of information technology has made cyberattacks complex. In the face of the great challenges posed by continuously changing networks to network security, this paper proposes a network exception detection approach that combines an improved inception module incorporating an attention mechanism and a Bi-LSTM. The inception module with the attention mechanism enhances the adaptability of the neural network to different spatial feature scales in the network stream, weakens irrelevant non-critical features, and exploits the advantages of the Bi-LSTM in terms of temporal features of the network stream to effectively improve the accuracy of the detection of network attacks.