Machine learning for encrypted malicious traffic detection: Approaches, datasets and comparative study

As people’s demand for personal privacy and data security becomes a priority, encrypted traffic has become mainstream in the cyber world. However, encryption is also shielding malicious illegal introduced by adversaries, from being detected. This especially so post-COVID-19 environment where growing rapidly. Common solutions that rely on plain payload content analysis such as deep packet inspection are rendered useless. Thus, machine learning based approaches have an important direction detection. In this paper, we formulate universal framework of detection techniques provided systematic review. Furthermore, current research adopts different datasets to train their models due lack well-recognized feature sets. result, model performance cannot be compared analyzed reliably. Therefore, analyse, process combine 5 sources generate comprehensive fair dataset aid future field. On basis, implement compare 10 algorithms. We then discuss challenges propose directions research.