Alice Chambers |
Microsoft has launched a new Security Copilot tool in preview to help defenders respond to security incidents with guidance powered by artificial intelligence.
Following quickly on from the release of Copilot in Microsoft 365, the new tool for security teams uses capabilities from OpenAI’s GPT-4 generative AI and global threat intelligence from Microsoft’s 65 trillion daily security signals to generate responses to prompts.
Users can ask a natural language question such as “What are all the incidents in my enterprise?” via the prompt bar and the solution will respond almost instantaneously with information. Security teams can then use this information to combat attacks.
“Our cyber-trained model adds a learning system to create and tune new skills,” said Vasu Jakkal, corporate vice president of security, compliance, identity and management at Microsoft, in a Microsoft blogpost. “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.”
Jaka explains that given AI-generated content can make mistakes, a closed-loop learning system means that it is continually learning from users and giving them the opportunity to give explicit feedback via the feedback feature that is built into the tool.
“As we continue to learn from these interactions, we are adjusting its responses to create more coherent, relevant and useful answers,” said Jakkal.
Microsoft Security Copilot will provide actionable insights to empower defenders
Meanwhile, Microsoft has also added new guidance controls and real-time access protections on Microsoft Entra, to simplify and secure the onboarding process for businesses. Microsoft Entra Identity Governance and Microsoft Entra Verified ID validate paperwork and online forms through trusted authorities to reduce the administrative burden for hiring teams.
“Microsoft Entra helps to secure access for new users in a company,” said Joy Chick, president of identity and network access at Microsoft in a Microsoft blogpost. “When you enable multifactor authentication, by all means, adopt the strongest methods. Older methods, such as SMS and voice calls, are simply less secure.”