Microsoft introduces an A.I. chatbot for cybersecurity experts

  • The Microsoft Security Copilot draws on OpenAI’s GPT-4 model and a security-specific model that Microsoft developed.
  • It knows about a customer’s security environment, but that data won’t be used to train artificial intelligence models.
  • Pricing information isn’t available yet.

Microsoft on Tuesday announced a chatbot designed to help cybersecurity professionals understand critical issues and find ways to fix them.

The company has been busy bolstering its software with artificial intelligence models from startup OpenAI after OpenAI’s ChatGPT bot captured the public imagination following its November debut.

The resulting generative AI software can at times be “usefully wrong,” as Microsoft put it earlier this month when talking up new features in Word and other productivity apps. But Microsoft is proceeding nevertheless, as it seeks to keep growing a cybersecurity business that fetched more than $20 billion in 2022 revenue.

The Microsoft Security Copilot draws on GPT-4, the latest large language model from OpenAI — in which Microsoft has invested billions — and a security-specific model Microsoft built using daily activity data it gathers. The system also knows a given customer’s security environment, but that data won’t be used to train models.

The chatbot can compose PowerPoint slides summarizing security incidents, describe exposure to an active vulnerability or specify the accounts involved in an exploit in response to a text prompt that a person types in.

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 service learn, Vasu Jakkal, corporate vice president of security, compliance, identity, management and privacy at Microsoft, told CNBC in an interview.