‘Security Copilot’ signals generative AI’s arrival to Microsoft’s cybersecurity business

Reading time icon 2 min. read


Readers help support MSpoweruser. We may get a commission if you buy through our links. Tooltip Icon

Read our disclosure page to find out how can you help MSPoweruser sustain the editorial team Read more

Microsoft officially integrated the power of AI into its security business. Called Microsoft Security Copilot, the tool is designed to aid cybersecurity professionals in better detecting and assessing tracks in a faster and more efficient manner.

Microsoft Security Copilot runs on Azure’s hyperscale infrastructure and employs the power of OpenAI’s recently-released GPT-4 generative AI model and Microsoft’s security-specific model. According to the software giant, the latter “incorporates a growing set of security-specific skills and is informed by Microsoft’s unique global threat intelligence and more than 65 trillion daily signals.”

As expected from the capabilities of the GPT-4 model, the Security Copilot can accept prompts via a prompt box to discover malicious behavior and threat signals and analyze data. What makes it special, however, is its ability to dig into the smallest detail and provide comprehensive incident summaries, allowing security professionals to spot all possible issues that need to be addressed and share the findings with other team members. Also, Microsoft said the tool, which integrates with the end-to-end Microsoft Security products, has a closed-loop learning system, allowing it to learn from users continuously.

“When Security Copilot receives a prompt from a security professional, it uses the full power of the security-specific model to deploy skills and queries that maximize the value of the latest large language model capabilities,” explained Vasu Jakkal, Microsoft CVP of security, compliance, identity, and management. “And this is unique to a security use-case. Our cyber-trained model adds a learning system to create and tune new skills. Security Copilot then can help catch what other approaches might miss and augment an analyst’s work. In a typical incident, this boost translates into gains in the quality of detection, speed of response and ability to strengthen security posture.”

The new tool joins Microsoft’s $20 billion per year cybersecurity business, which also offers Microsoft Defender, Microsoft Entra, Microsoft Purview, and Microsoft Sentinel. Security Copilot has become one of the newest AI-powered products of the software company, which aims to inject the technology across all its offerings. Recently, Microsoft revealed that it integrated GPT-4 into Bing as early as February. Aside from this, the company announced other AI integrations into its products and other businesses, including GitHub’s “Copilot X,” LinkedIn, and Dynamics 365 Copilot.

More about the topics: ai, GPT-4, openAI, security, Security Copilot