Malicious Mining Behavior Detection System of Encrypted Digital Currency Based on Machine Learning

Abstract

With the gradual increase of malicious mining, a large amount of computing resources are wasted, and precious power resources are consumed maliciously. Many detection methods to detect malicious mining behavior have been proposed by scholars, but most of which have pure defects and need to collect sensitive data (such as memory and register data) from the detected host. In order to solve these problems, a malicious mining detection system based on network timing signals is proposed. When capturing network traffic, the system does not need to know the contents of data packets but only collects network flow timing signals, which greatly protects the privacy of users. Besides, we use the campus network to carry out experiments, collect a large amount of network traffic data generated by mining behavior, and carry out feature extraction and data cleaning. We also collect traffic data of normal network behavior and combine them after labeling. Then, we use four machine learning algorithms for classification. The final results show that our detection system can effectively distinguish the normal network traffic and the network traffic generated by mining behavior.