Generating Packet-Level Header Traces Using GNN-powered GAN

Abstract

This study presents a novel method combining Graph Neural Networks (GNNs) and Generative Adversarial Networks (GANs) for generating packet-level header traces. By incorporating word2vec embeddings, this work significantly mitigates the dimensionality curse often associated with traditional one-hot encoding, thereby enhancing the training effectiveness of the model. Experimental results demonstrate that word2vec encoding captures semantic relationships between field values more effectively than one-hot encoding, improving the accuracy and naturalness of the generated data. Additionally, the introduction of GNNs further boosts the discriminator's ability to distinguish between real and synthetic data, leading to more realistic and diverse generated samples. The findings not only provide a new theoretical approach for network traffic data generation but also offer practical insights into improving data synthesis quality through enhanced feature representation and model architecture. Future research could focus on optimizing the integration of GNNs and GANs, reducing computational costs, and validating the model's generalizability on larger datasets. Exploring other encoding methods and model structure improvements may also yield new possibilities for network data generation. This research advances the field of data synthesis, with potential applications in network security and traffic analysis.