In this age, where cryptocurrencies are slowly creeping into the banking services and making a name for them, it is becoming crucially essential to figure out the security concerns when users make transactions. This paper investigates the untrusted users of cryptocurrency transaction services, which are connected using smartphones and computers. However, as technology is increasing, transaction frauds are growing, and there is a need to detect vulnerabilities in systems. A methodology is proposed to identify suspicious users based on their reputation score by collaborating centrality measures and machine learning techniques. The results are validated on two cryptocurrencies network datasets, Bitcoin-OTC, and Bitcoin-Alpha, which contain information of the system formed by the users and the user's trust score. Results found that the proposed approach provides improved and accurate results. Hence, the fusion of machine learning with centrality measures provides a highly robust system and can be adapted to prevent smart devices' financial services.