Unsupervised Machine Learning: Fighting Cross-Channel FraudThetaRay's James Heinzman Shares Insights on Countering Sophisticated Fraud Techniques
Unsupervised machine learning is essential to mitigate the sophisticated cross-channel fraud techniques attackers are using to take advantage of the multiple silos and security gaps at financial institutions, says ThetaRay's James Heinzman.
"There are many silos, including business silos, data silos, product silos, and regional silos. ... There is so much data now that it is hard to find things that are in plain sight," he says in an interview with Information Security Media Group. "To be able to have the tools to get an enterprise view, and to be able to get actionable insight from across these disparate data sources is a big deal." (See: Breaking Down Legacy Silos in Security)
Attackers are exploiting these cyber gaps and combining them with other fraud channels. Conventional rule-based defensive techniques and supervised machine learning-based methods are not very good at detecting these sophisticated attacks, he says. Attackers are beginning to study and mimic employee behavior in complex ways, and they have access on the dark web to security playbooks for older rules-based and supervised strategies - which puts the defender several steps behind, he contends (see: Breaking Down Silos to Make Intelligence Actionable).
In this audio interview (see player link below image), Heinzman also discusses:
- Why unsupervised machine learning is essential (see: Why Big Data, Machine Learning Are Critical to Security);
- How attackers are combining cyber with other fraud channels;
- What to look for when choosing a machine learning technology for fighting fraud.
As executive vice president of financial services solutions at ThetaRay, Heinzman oversees strategy for the company's financial services solutions and its financial crime analytics platform. He has over 25 years of risk and compliance experience, and has held positions such as chief compliance officer, head trader and senior operations director for leading financial services companies. He formerly served as executive vice president of risk and compliance at SunGard, managing director of global compliance solutions at Nice Actimize, and managing director for global equities at Bear Sterns.