Catching the Unknown Unknowns in Banking Cyber Attacks Using Unsupervised Machine Learning

Catching the Unknown Unknowns in Banking Cyber Attacks Using Unsupervised Machine Learning

Juniper Research forecasts that the annual cost of data breaches will increase from $3 trillion in 2019 to $5 trillion in 2024. For financial institutions, the costs of risk mitigation are well known: 6-14% of annual IT budgets, or around 0.2% to 0.9% of company revenue.

Most in the financial industry have embraced various AI/ML techniques to essentially allow the model to learn the rules required to detect attacks. The hypothesis has been that with enough sample data, you can build supervised models to detect never-before-seen-attacks. But if you’re trying to train models to detect unknown attacks, you need data representative of known attacks.

Is there a better way to identify this sort of activity (and the data trail it creates) with low errors?

This whitepaper will guide you in the right direction when dealing with discovering and detecting unknown attacks whose signatures are also unknown.




Around the Network

Our website uses cookies. Cookies enable us to provide the best experience possible and help us understand how visitors use our website. By browsing bankinfosecurity.com, you agree to our use of cookies.