Intelligent Network Security Optimization Algorithm Based on Cnns

Abstract

To enhance the precision of security risk assessment and real-time control in edge-based intelligent networks, this article presents a novel risk assessment and control approach leveraging convolutional neural networks (CNNs). This method significantly improves on traditional intelligent network security risk assessment techniques, integrating CNN-based models to achieve higher accuracy and robustness. By incorporating genetic algorithms and proportional integral derivative control optimization, the proposed approach further ensures stability across intelligent network operations. Using the KDDCup99 network security attack database for evaluation, results demonstrate that this approach achieves a high accuracy rate and low false alarm rate. Additionally, the output signal amplitude closely aligns with the expected amplitude, showing only a 0.02 deviation, while maintaining low evaluation and control times. This ensures comprehensive security across edge intelligent systems, addressing key latency and precision requirements and achieving optimal control effects.