Microsoft Security Copilot leverages ChatGPT to help defenders understand attacks

Share post:

Microsoft has answered the question of what solution providers can do with ChatGPT: Incorporate it into a tool for security analysts.

The tool is an AI assistant called Microsoft Security Copilot, a service to quickly detect and respond to threats and help analysts better understand the threat landscape overall.

Now in private preview, Security Copilot will combine the search and natural language reply capabilities of ChatGPT4 with Microsoft’s threat intelligence capabilities.

If a company gets an endpoint alert from Microsoft Defender, a threat analyst could ask Security Copilot to assemble a story on the compromise, including a graphic of the attack chain that can be shared with others on the security team. It could reverse-engineer an attack script or tell the analyst how many email messages are associated with the attack.

This Microsoft video better shows how it works:

Security Copilot will also continually learn and improve to help ensure that security teams are operating with the latest knowledge of attackers, their tactics, techniques and procedures, Microsoft said.

Security Copilot doesn’t always get everything right, the company admitted. In fact, query responses say content should be verified before sharing. But, Microsoft said, Security Copilot is a closed-loop learning system that continually learns from users’ feedback.

The company stressed that each organization’s implementation of Copilot will use only its own corporate data. There will be no sharing of security data across customers to help the platform learn.

At the moment, it only integrates with Microsoft products like Defender, Entra, Intune, Priva and Purview. But the company promises it will integrate with other companies’ products, many of whom would be Microsoft partners.

Microsoft emphasized that Security Copilot can help inexperienced members of security teams better fight attacks.

The company didn’t say when Security Copilot will be generally released, nor did it say how much it will cost.

“Today the odds remain stacked against cybersecurity professionals. Too often, they fight an asymmetric battle against relentless and sophisticated attackers,” said Vasu Jakkal, corporate vice-president of Microsoft Security. “With Security Copilot, we are shifting the balance of power into our favor. Security Copilot is the first and only generative AI security product enabling defenders to move at the speed and scale of AI.”

In a commentary, Forrester Research senior analyst Allie Mellen said Security Copilot is poised to become the connective tissue for all Microsoft security products and, importantly, will integrate with third-party products as well. This is a hard and fast requirement for an assistant that can provide comprehensive and consistent value, she said.

“This is the first time a product is poised to deliver on true improvement to investigation and response with AI,” she said. “With this announcement, we leave an era behind where AI was relegated to detection, and enter one where AI has the potential to improve one of the most important issues in security operations: analyst experience (AX).”

MORE TO COME

The post Microsoft Security Copilot leverages ChatGPT to help defenders understand attacks first appeared on IT World Canada.
Howard Solomon
Howard Solomonhttps://www.itworldcanada.com
Currently a freelance writer, I'm the former editor of ITWorldCanada.com and Computing Canada. An IT journalist since 1997, I've written for ITBusiness.ca and Computer Dealer News. Before that I was a staff reporter at the Calgary Herald and the Brampton (Ont.) Daily Times.

SUBSCRIBE NOW

Related articles

Microsoft reveals critical security flaw affecting Android apps

Microsoft has identified a serious vulnerability in Android apps that could allow malicious software to hijack legitimate apps...

Chinese government websites “Riddled with security flaws” say researchers

A recent study conducted by researchers from the Harbin Institute of Technology reveals significant security issues plaguing Chinese...

Cyber Security Today, May 3, 2024 – North Korea exploits weak email DMARC settings, and the latest Verizon analysis of thousands of data breaches

This episode reports on warnings about threats from China, Russia and North Korea, the hack of Dropbox Sign's infrastructure

Hashtag Trending for World Password Day, Thursday, May 2nd, 2024

Security firm Okta warns of an unprecendented password stuffing attack that is piggybacking on regular user’s mobile and...

Become a member

New, Relevant Tech Stories. Our article selection is done by industry professionals. Our writers summarize them to give you the key takeaways