November 12, 2021
Due to the pseudo-anonymity of the Bitcoin network, users can hide behind their bitcoin addresses that can be generated in unlimited quantity, on the fly, without any formal links between them. Thus, it is being used for payment transfer by the actors involved in ransomware and other illegal activities. The other activity we consider is related to gambling since gambling is often used for transferring illegal funds. The question addressed in this talk is that given temporally limited graphs of Bitcoin transactions, to what extent can one identify common patterns associated with these fraudulent activities and apply them to find other ransomware actors. The problem is rather complex, given that thousands of addresses can belong to the same actor without any obvious links between them and any common pattern of behavior. We introduce and apply new algorithms for local clustering and supervised graph machine learning for identifying malicious actors. We show that very local subgraphs of the known such actors are sufficient to differentiate between ransomware, random and gambling actors with 85% prediction accuracy on the test data set.
Dr. Siddhartha “Sid” Dalal is a Professor of Practice at Columbia University in the Applied Analytics program and in the Statistics Department, teaching and researching Blockchain/Cryptocurrencies and Machine Learning. Prior to joining Columbia University, he was Chief Data Scientist and Senior Vice President at AIG in charge of research and development (R&D) that included the creation and application of artificial intelligence (AI), Statistics and CS to Computer Vision, Natural Language Processing, and Sensors/IOT for managing risks. He came to AIG from RAND Corporation where he was the Chief Technology Officer and from Xerox as the Vice President of Research, starting his career at Bell Labs and Bellcore where he was Chief Scientist and Executive Director.
Dr. Dalal has over 100 peer-reviewed publications, patents, and monographs covering the areas of risk analysis, medical informatics, Bayesian statistics and economics, image processing, and sensor networks. At Rand, he was responsible for the creation of technology and spinning-off of Praedicat, Inc., a casualty insurance analytics company measuring and quantifying environmental risks. He has received several awards including from IEEE, ASA, and ASQ for his work on risk analysis of challenger disaster and for measuring and managing software risks. Dr. Dalal is a member of the Army Science Board appointed by Secretary of Defense to advise Army on Technologies.