A Network Intrusion Detection System with Broadband WO3–x/WO3–x‐Ag/WO3–x Optoelectronic Memristor

• Published in: Advanced functional materials Vol. 34; no. 23
• Main Authors: Yang, Wenhao, Kan, Hao, Shen, Guozhen, Li, Yang
• Format: Journal Article
• Language: English
• Published: Hoboken Wiley Subscription Services, Inc 06.06.2024
• Subjects: Artificial neural networks; Broadband; Central processing units; CPUs; intrusion detection system; Intrusion detection systems; KDDCup‐99 dataset; Memristors; neural network; optoelectronic memristor; Optoelectronics; Power consumption; Power management; WO3–x
• DOI: 10.1002/adfm.202312885
• ISSN: 1616-301X

Real‐time intrusion detection system based on the von Neumann architecture struggle to balance low power consumption and high computing speed. In this work, a strategy for network intrusion detection system based on the WO3–x/WO3–x‐Ag/WO3–x structured optoelectronic memristor overcoming the aforementioned issues is proposed and demonstrated. Through the modulation of electrical signals, the memristor successfully simulates a series of important synaptic functionalities including short‐term/long‐term synaptic plasticity. Meanwhile, when subjected to light stimulus, it demonstrates remarkable synaptic behaviors in terms of long/short‐term memory and “learning‐forgetting‐relearning.” Based on this memristor array, a convolutional neural network is constructed to recognize abnormal network records within the KDDCup‐99 dataset accurately and efficiently. The power consumption (10–6 W) is over seven orders of magnitude lower than that of central processing unit, etc. Subsequently, an intrusion detection system is established to integrate collection, processing, and detection of real‐time network data, successfully classifying various types of network records. Hence, this work is expected to promote the development of high‐density storage and neuromorphic computing technology, and provides an application idea for intelligent electronic devices. A broadband optoelectronic synapse based on WO3–x/WO3–x‐Ag/WO3–x is proposed, which achieves a variety of fundamental and advanced electro‐optical synaptic behaviors. Because of the low power consumption advantage demonstrated by memristor array, the proposed intrusion detection system (IDS) can classify types of network records from KDDCup‐99 dataset and real‐time network data.