Method for defending distributed denial of service attack of industrial network system

Abstract

The invention discloses a method for defending distributed denial of service attack of an industrial network system, and belongs to the technical field of network security defense. According to the method, deep learning and software defined network technologies are fused to construct an industrial network for preventing DDoS attacks. The deep learning technology for attack detection has the characteristics of flexibility and accuracy, and the SDN realizes the overall network management and flow control of the industrial network. According to the invention, a deep learning classification algorithm is constructed based on AC-GAN, the generator can generate data for a specific label, and the discriminator improves the quality of the generated data by reconstructing label information. According to the method, the sensitivity of the model is improved by generating the adversarial attack sample, and the accuracy of detecting the adversarial DDoS attack in the software defined industrial network is improved. According to the method, real-time flow information is extracted and monitored through the SDIN controller, when attack flow is detected, the system can automatically trigger an attack relieving function, add firewall rules and issue abandoned flow table entry strategies, and therefore DDoS attacks are relieved in time.

Description

technical field [0001] The invention relates to a method for defending distributed denial of service (Distributed Denial of Service, DDoS) attacks in an industrial network system based on deep learning and a software-defined network, and belongs to the technical field of network security defense. Background technique [0002] With the continuous development of intelligent manufacturing technology, new manufacturing modes such as personalized customization and networked collaboration have been widely developed. These new manufacturing models require frequent data exchange over the network between manufacturing machines and industrial information systems that dynamically adjust to changes in orders, business, and the environment. [0003] However, the existing industrial network architecture cannot meet the requirements of the above-mentioned manufacturing mode. For example, there are many industrial network protocols, forming a complex industrial heterogeneous network, which...

AI Technical Summary

Problems solved by technology

Second, the centralized SDN controller is a common attack target and can easily cause a single point of failure

However, deep learning models often become sensitive when detecting adversarial DDoS attacks

Adversarial attacks usually refer to the situation where the attacker deliberately adds some kind of imperceptible interference to the input sample, which leads to the misjudgment of the prediction model.

Images