Payload Encoding Representation from Transformer for Encrypted Traffic Classification

• 作者: HE Hongye YANG Zhiguo CHEN Xiangning
• 来源期刊: 中兴通讯技术（英文版）
• 年，卷（期）: 2021,（4）
• 所属期刊栏目: Research Paper
• 页码范围: 90-97
• 页数: 8页
• 语种: 英文
• DOI: 10.12142/ZTECOM.202104010

摘要

Traffic identification becomes more important, yet more challenging as related encryption techniques are rapidly developing nowadays. Unlike recent deep learning methods that apply image processing to solve such encrypted traffic problems, in this pa?per, we propose a method named Payload Encoding Representation from Transformer (PERT) to perform automatic traffic feature extraction using a state-of-the-art dynamic word embedding technique. By implementing traffic classification experiments on a pub?lic encrypted traffic data set and our captured Android HTTPS traffic, we prove the pro?posed method can achieve an obvious better effectiveness than other compared baselines. To the best of our knowledge, this is the first time the encrypted traffic classification with the dynamic word embedding has been addressed.