2021/02/21 by Aaron Zimba, Zimba, Aaron, Mumbi Chishimba +5
Computer Science · #Advanced Malware Detection Techniques #Computer science #Computer security #Cryptocurrency #Cryptography and Security (cs.CR) #Cybercrime #Data mining #Data science #Digital Media Forensic Detection #Digital and Cyber Forensics #Digital forensics #FOS: Computer and information sciences #Law enforcement #Network security #Process (computing) #The Internet #World Wide Web #cs.CR
paper · pdf · doi:10.48550/arxiv.2102.10634
arxiv created 2021/02/21 · openalex publication_date 2021/02/21 · arxiv updated 2021/02/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Cryptocurrencies have emerged as a new form of digital money that has not\nescaped the eyes of cyber-attackers. Traditionally, they have been maliciously\nused as a medium of exchange for proceeds of crime in the cyber dark-market by\ncyber-criminals. However, cyber-criminals have devised an exploitative\ntechnique of directly acquiring cryptocurrencies from benign users' CPUs\nwithout their knowledge through a process called crypto mining. The presence of\ncrypto mining activities in a network is often an indicator of compromise of\nillegal usage of network resources for crypto mining purposes. Crypto mining\nhas had a financial toll on victims such as corporate networks and individual\nhome users. This paper addresses the detection of crypto mining attacks in a\ngeneric network environment using dynamic network characteristics. It tackles\nan in-depth overview of crypto mining operational details and proposes a\nsemi-supervised machine learning approach to detection using various crypto\nmining features derived from complex network characteristics. The results\ndemonstrate that the integration of semi-supervised learning with complex\nnetwork theory modeling is effective at detecting crypto mining activities in a\nnetwork environment. Such an approach is helpful during security mitigation by\nnetwork security administrators and law enforcement agencies.\n