Container Security Assessment and Reinforcement Technology Integrating Big Data and Intelligent Algorithms

As a lightweight virtualization solution, container technology has been widely applied in fields such as cloud computing and micro services. The security issues of container technology are becoming increasingly prominent, becoming a key factor restricting its development. This study aims to explore the integration of big data and intelligent algorithms, especially the application of Convolutional Neural Network (CNN) in container security assessment and reinforcement, and compare it with Long Short-Term Memory (LSTM) and Graph Neural Network (GNN). By collecting and preprocessing a large amount of container operation data, this study constructed a CNN model and conducted comparative experiments with LSTM and GNN models to evaluate the performance of the three models in terms of interpretability, reinforcement effect, and computational resource consumption. The research methods of this article include selection of intelligent algorithms, data collection and preprocessing, construction of security evaluation models, and implement of security reinforcement strategies. In the model construction phase, this study adopted a CNN model, utilizing its advantages in feature learning to extract and classify security threats through a combination of convolutional layers, pooling layers, and fully connected layers. In terms of security reinforcement strategies, this study implemented a series of measures, including mirror security, minimum permission principle, network isolation, runtime monitoring, etc., to improve the security of container environments. The data indicated that CNN performed excellently in interpretability, with significant reinforcement effects, and the lowest CPU utilization rate in terms of computing resource consumption was only 4.2%. These findings indicate that CNN models have great potential in container security assessment and reinforcement tasks, effectively improving the security of container environments and reducing the risk of security threats.