An Anomalous Behavior Detection Method for Complex Networks Based on Image Processing and Protocol Evolution Modeling

With the rapid development of information technology, complex networks are increasingly vulnerable to abnormal behaviors such as malicious attacks and data breaches due to their growing scale and structural complexity.Traditional detection methods often struggle in dynamic network environments due to insufficient utilization of temporal features and lack of protocol evolution analysis, resulting in suboptimal detection accuracy.Existing studies based on conventional machine learning typically ignore the temporal characteristics of network behaviors and the evolutionary nature of protocols.Similarly, image processing techniques alone fail to incorporate protocol-level information, while static protocol models cannot adapt to dynamically changing scenarios, leading to incomplete extraction of essential features of anomalous behaviors.To address these challenges, this paper proposes a novel detection method that integrates image processing with protocol evolution modeling.The main contributions are as follows: (1) A method for visual mapping of temporal network behaviors is designed, converting dynamic behaviors into interpretable image features; (2) A protocol evolution prediction model is constructed, combining time series analysis with machine learning techniques to capture the dynamics of protocol changes; (3) A multimodal behavior recognition model is developed, integrating image features with protocol evolution features to accurately detect anomalous behaviors.By leveraging cross-disciplinary techniques, this study overcomes the limitations of existing approaches in temporal feature utilization, dynamic protocol modeling, and multimodal data fusion.It offers a novel framework that supports both visual analysis and dynamic mechanism modeling, contributing to improved accuracy and robustness in detecting anomalous behaviors in complex networks.