Microsoft Introduces GPT-4 Chatbot for Security Experts

Microsoft has just introduced a new A.I. chatbot specifically designed to assist cybersecurity researchers in understanding critical issues and finding ways to fix them.

Called the Microsoft Security Copilot, it is based on OpenAI’s latest GPT-4 model, and a security-specific model Microsoft built using daily activity data it gathers.

According to CNBC, Microsoft engineers have been using the Security Copilot to do their jobs, as confirmed by Microsoft’s VP of security Vasu Jakkal.

“It can process 1,000 alerts and give you the two incidents that matter in seconds,” Jakkal said during an interview.

The chatbot can compose PowerPoint slides summarizing security incidents, and even specify the accounts involved in an exploit in response to a user text prompt.

Microsoft says this type of assistance can help companies that run into trouble hiring experts and end up hiring inexperienced employees.

Jakkal explained that a user can hit a button to confirm an answer if it’s right or select an “off-target” button to signal a mistake. That sort of input will help the Copilot learn.

“There’s a learning curve, and it takes time,” Jakkal said. “And now Security Copilot with the skills built in can augment you.”

He also hopes that many workers inside a given company will use it, rather than just a handful of executives.

Security Copilot will be available to download a small set of Microsoft clients in a private preview. It will work with Microsoft security products such as Sentinel for tracking threats.

The company has not yet revealed how much Security Copilot will cost when it becomes more widely available.