Deep Contrastive Clustering for Protocol Analysis in 5G Network Engineering

With the widespread adoption of 5G networks in satellite communication and vehicular communication systems, the complexity of communication and signaling interactions has significantly increased. Traditional protocol analysis methods primarily focus on high-level structured data, often neglecting the low-level binary data critical for understanding 5G-specific protocols. This paper proposes a novel approach that employs a deep contrastive clustering framework to analyze and classify unknown protocols in 5G communication networks. The proposed method leverages depthwise separable convolutions for feature extraction, transforming binary protocol data into structured feature representations while significantly reducing computational overhead. Additionally, by integrating contrastive learning into the clustering process, the framework enhances the discrimination of protocol embeddings through a positive-negative sample feedback mechanism, ensuring more accurate clustering results. Additionally, this paper collected and analyzed a comprehensive dataset of 5 G protocols, which includes wireless access layer protocols and core network communication protocols.