Identifying ransomware actors in the bitcoin network
This technology is an algorithm specifically designed to differentiate between normal bitcoin transactions and malicious transactions, to identify ransomware attackers.
Unmet Need: Systems to detect and differentiate bitcoin transactions
The rise of ransomware attacks, which has already extorted over a billion in bitcoin, has highlighted the difficulty in identifying malicious actors due to the pseudo-anonymous nature of blockchain transactions. Current methods either lack precision by grouping numerous addresses into one cluster or necessitate additional unavailable information like IP addresses. As such, more accurate and efficient techniques to identify and track cybercriminals involved in ransomware attacks are needed.
The Technology: Algorithm for Precise Transaction Classification
This technology utilizes clustering and supervised machine learning algorithms to identify malicious actors using publicly available blockchain data. These algorithms take advantage of the behaviors of scam artists, including using multiple addresses to pay for one transaction and quickly move bitcoin from address to address. The technology was able to differentiate between ransomware, gambling transactions, and normal bitcoin transactions with 85% prediction accuracy on the test data set.
Applications:
- Anonymity disruption for unveiling ransomware attackers
- Precise clustering for identifying scam transactions
- Future scammer attack prevention
- Filtering scam calls and preventing fraud
Advantages:
- Enhances precision for accurate identification of malicious actors
- Eliminates the need for additional information by using publicly available data from blockchain
- Swift detection for quick response times
Lead Inventor:
Patent Information:
Patent Pending
Related Publications:
Tech Ventures Reference:
IR CU22320
Licensing Contact: Greg Maskel