Some Cybersecurity Pros Are Already Using ChatGPT With Microsoft Security Tools
While Microsoft is planning to widely deploy the AI chatbot within its product portfolio, some cybersecurity professionals are already tying together ChatGPT with the Microsoft Sentinel security analytics platform.
While OpenAI backer Microsoft has very been clear that it has big plans for integrating its platforms with ChatGPT, some cybersecurity pros aren’t waiting on Microsoft.
In recent days, several cybersecurity professionals have published information online about how to integrate the AI-powered chatbot with Microsoft Sentinel, the widely used Microsoft cybersecurity analytics platform.
[Related: 5 Big Pros And Cons Of ChatGPT For Cybersecurity]
“By harnessing the power of ChatGPT, I believe it is possible to speed up and simplify the incident handling process, making it more efficient and effective for all involved,” wrote IT security pro Antonio Formato in a post on Medium Monday.
Another recent Medium post by cyber pro Zubair Rahim included step-by-step instructions for connecting ChatGPT with Microsoft Sentinel. “Integrating ChatGPT with Microsoft Sentinel for incident management offers numerous benefits such as automating responses, providing accurate and timely answers, and streamlining incident management workflow,” Rahim wrote.
Microsoft Sentinel is among the company’s key cybersecurity offerings and now has more than 20,000 customers, up from 15,000 a year ago, Microsoft disclosed last week.
The potential is definitely there for OpenAI’s ChatGPT to help security analysts, who work with SIEM (security information and event management) tools like Microsoft Sentinel, to help automate and expedite some of the typically manual analysis of security incidents, according to Michael Montagliano, CISO at Atlanta-based solution provider ProArch.
At this early stage, though, more testing of the types of integration methods that are now being posted online is definitely necessary, which ProArch plans to do, Montagliano told CRN.
“We are going to test that integration into Sentinel in a lab environment,” he said. “One of the things you have to be cautious about is is that accurate? Is it dependable?”
Robert Boyce, Accenture’s global lead for cyber resilience services, told CRN last week that Accenture Security sees major potential in using ChatGPT’s capabilities for automating some of the work involved in cyberdefense. While there has been major attention paid to the possible nefarious uses of the chatbot by hackers, it’s clear that the tool “helps reduce the barrier to entry with getting into the defensive side as well,” Boyce said.
Last week, Microsoft said it’s making a new “multiyear, multibillion-dollar investment” into OpenAI, which reportedly amounts to $10 billion. Microsoft had previously invested more than $3 billion into OpenAI starting in 2019, and OpenAI uses Microsoft Azure for its cloud infrastructure.
Earlier this month, Microsoft announced the general availability of its Azure OpenAI Service, which leverages OpenAI technologies including GPT-3.5. The company noted that “customers will also be able to access ChatGPT—a fine-tuned version of GPT-3.5 that has been trained and runs inference on Azure AI infrastructure—through Azure OpenAI Service soon.”
During Microsoft’s quarterly call with analysts last week, Chairman and CEO Satya Nadella said that the company plans to deploy OpenAI technology “across our consumer and enterprise products as we continue to push the state of the art in AI.”
OpenAI, which is also behind the DALL-E 2 image generator, and whose backers include Microsoft, first introduced ChatGPT in late November. While it’s been massively popular among users, it’s come under fire from a number of critics, including some of Microsoft’s competitors. For instance, Amazon Web Services CTO Werner Vogels Tuesday slammed ChatGPT as being “not concerned about the truth.”