Clipped from: https://www.thehindubusinessline.com/info-tech/microsoft-launches-chatgpt-enabled-security-solution/article66705747.ece
Microsoft’s Security Copilot identifies lurking problems, constantly learns
Even as coders, academicians, doctors and lawyers are using ChatGPT and other generative AI tools, Microsoft has launched Security Copilot, a security solution laced with OpenAI’s ChatGPT.
This will improve the quality of detection, speed of response, and security posture, the company said.
It will help defenders respond to security incidents within minutes instead of hours or days. It delivers step-by-step guidance and context through a natural language-based investigation experience that accelerates investigation and response, it said.
Attackers hide behind noise and weak signals.
The solution can answer security-related questions — from basic to complex.
“With Microsoft Security Copilot, we’re combining advanced AI models with domain- and task-specific data, context, and skills to empower every defender and transform every aspect of SOC (security operations centre) productivity,” Microsoft CEO Satya Nadella said in a tweet.
The launch of Security Copilot follows a Microsoft initiative to integrate ChatGPT capabilities to its Office365 suite. The Redmond-based company is a major investor in OpenAI, which hit headlines after it launched the generative AI solution ChatGPT that can churn out human-like answers.
Terming the solution an ‘end-to-end defence at machine speed and scale’, Microsoft said it is the first that enables defenders to move at the speed and scale of artificial intelligence.
“Security Copilot combines this advanced large language model (LLM) with a security-specific model from Microsoft,” Vasu Jakkal, Corporate Vice-President (Security, Compliance, Identity, and Management), Microsoft, said in a blog.
How it works
When Security Copilot receives a prompt from a security professional, it uses the security-specific model to deploy skills and queries that maximise the value of the latest LLM capabilities.
“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,” she said.
It might not always get everything right. AI-generated content can contain mistakes.
“But Security Copilot can continually learn from users and give them the opportunity to give explicit feedback with the feedback feature that is built directly into the tool,” she explained.
Over a period of time, the tool will be integrated with other security products of Microsoft. It will later be expanded to third-party products as well.
“We’ve built Security Copilot with security teams in mind — your data is always yours and stays within your control,” she said.