CapsuleFormer: A Capsule and Transformer combined model for Decentralized Application encrypted traffic classification

Xiang Zhou, Xi Xiao, Qing Li, Bin Zhang, Guangwu Hu, Xiapu Luo, Tianwei Zhang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review


Network traffic classification plays a crucial role in both network management and monitoring. Recently, an increasing number of Decentralized Applications (DApps) are appearing on various blockchain platforms. DApps employ encryption techniques such as SSL/TLS to safeguard the data transmitted over the network, making it more challenging to do traffic classification. In this paper, to tackle the challenge of insufficient classification accuracy in the existing classification of encrypted DApp traffic, we present Capsule-
Former, a novel encrypted traffic classification model for DApps. CapsuleFormer utilizes capsule neurons instead of traditional scalar neurons, where the neurons within the capsule embody various attributes of particular entities. Furthermore, Transformer blocks are adopted to generate a high-dimensional representation of the capsule activation vector. Thus, CapsuleFormer has the capability to extract potential features from the encrypted traffic patterns of DApps. Moreover, we collect and open a dataset of more than 700,000 encrypted traffic flows from 10 different types of DApps. The results of the experiments on the dataset demonstrate that CapsuleFormer is superior to the current methods, with an accuracy rate of 98.7%.
Original languageEnglish
Title of host publicationThe 19th ACM ASIA Conference on Computer and Communications Security
Publication statusPublished - Jul 2024


Dive into the research topics of 'CapsuleFormer: A Capsule and Transformer combined model for Decentralized Application encrypted traffic classification'. Together they form a unique fingerprint.

Cite this