According to the United Nations, between 2% and 5% of gross domestic product (GDP) is laundered globally every year, which amounts to $800 billion to $2 trillion. Recognizing the need to move beyond a manual and fragmented monitoring system, Consilient built an intelligent, collaborative and always-on solution that leverages federated learning and Intel SGX to detect financial fraud.
By automating this process through federated learning, access to multiple datasets, databases and jurisdictions are encrypted without ever revealing the data or sensitive customer information to the different parties involved. Government and financial institutions can use this new platform to more accurately and efficiently detect illicit activity, with lower false positive rates, helping to combat financial crime, thwart higher-value money laundering, and enable legitimate individuals and businesses to manage risk more effectively.
“When banks try to detect illicit and fraudulent activity, the system is highly inefficient and ineffective, with over 95% of transaction monitoring rendering false positives and institutions unable to see risk beyond their own walls,” said Juan Zarate, global co-managing partner and chief strategy officer at K2 Integrity and first-ever assistant secretary of the U.S. Treasury for Terrorist Financing and Financial Crimes. “With Consilient’s federated machine learning technology, backed by Intel SGX, we are redesigning the way financial institutions and authorities discover and prevent financial crime risk dynamically and securely. This new approach allows organizations to save costs, redeploy personnel, and manage and prioritize more serious illicit finance risks efficiently and effectively.“
Federated learning is a privacy-preserving machine learning (ML) technique and confidential computing model that enables AI training without centralizing data. Consilient has created a behavioral-based, ML-driven platform that runs on its DOZER™ technology. ML models can be trained across multiple datasets to detect and analyze “normal” and “abnormal” patterns that humans and most current technologies cannot. This allows participating institutions, authorities and regulators to collaborate while uncovering and managing systemic risks more effectively, efficiently and sustainably without putting private data at risk.
This computing model is made possible through Intel SGX, which uses a hardware-based trusted execution environment (TEE) to help isolate and protect specific application code and data in memory. The technology helps ensure the root of trust is limited to a small portion of the central processing unit’s hardware and the ML application itself, reducing the attack surface for potential threats, and better protecting the confidentiality and integrity of code and data.