Using Unsupervised Learning to detect Fraud in Cryptocurrency

Bitcoin, the most popular form of cryptocurrency, operates independently of central banks or governmental entities. The emphasis on anonymity complicates the task of tracing cryptocurrency payments linked to illicit activities or criminal transactions. Consequently, ransomware developers exploit this environment to extort ransom by encrypting valuable user information. Numerous research endeavors have explored the application of machine learning techniques to detect fraudulent activities within cryptocurrency transactions. However, there is a notable absence of studies showcasing the practical implementation of such methods using real-time blockchain data. The present study is structured into two main sections. Firstly, we delineate the development of various features utilized for training purposes. Subsequently, our approach will be validated using real-time Bitcoin data. The other section highlights the use of open source investigation tool (OSINT) to carry forward the cryptocurrency investigation by taking the input from previous findings. OSINT involves the retrieval of information from a range of publicly accessible data sources, while offering a viable approach to address the difficulties associated with extracting and aggregating intelligence from diverse publicly available information channels and social platforms. Thus narrowing down the search investigation by exploiting the pseudonymity of Bitcoin and tracing back the wallet and IP addresses’ digital and physical identity.