While other tools might do this, Microsoft argues that Security Copilot is better with support of generative AI models from OpenAI, such as the recently launched GPT-4.
Unique to the tool, the ability to rely on a cyber-trained model, a learning system to create new skills. Security Copilot can help catch what other approaches might miss and augment an analyst’s work. The idea is to gain detection and a speedier response time. Both can strengthen security, according to Vasu Jakkal, Microsoft corporate vice president of security, compliance, identity, and management.
"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," Jakkal wrote in a post.
Security Copilot will combine Microsoft's threat intelligence with the expertise to augment the work of security professionals through an easy-to-use AI assistant.
Jakkal wrote that the model is not trained on customer data. The data "is not used to train the foundation AI models and, in fact, it is protected by the most comprehensive enterprise compliance and security controls," he wrote.
The data remains private, but each user interaction can be shared with other team members to accelerate incident response, collaborate more effectively on complex problems and develop collective skills.