Bank built its own AI threat hunter because vendors can't

"When I joined [six years ago], we ingested 80 million signals a week. Last week it was 400 billion. You cannot manage that with traditional cyber defences. The lure changed, but the backend was the same. Since the advent of AI, the volume of attacks the bank detects has also increased significantly."

"I wanted our first-level analysts the access the same knowledge our senior people have, in the fastest way. That was the tipping point: How do I take scale off the table, and how do I ensure all our agents are working in cyber in 20 years time instead of burning out?"

Commonwealth Bank's General Manager of Cyber Defence Operations Andrew Pade revealed that the bank built its own agentic AI threat hunting tools due to vendor inability to develop solutions fast enough for emerging AI-powered threats. The bank's daily threat signals have grown from 80 million six years ago to over 4 billion currently, with AI contributing significantly to this increase. Pade noted that attackers reuse backend code across multiple campaigns, often containing AI coding tool artifacts. Traditional cyber defenses cannot manage this scale. The bank also aims to address cybersecurity workforce challenges by providing junior analysts access to senior-level knowledge through AI tools, reducing burnout and career attrition in the field.

Read at Theregister