Login
iscover
Share this article on:
Powered by
MOMENTUM
MEDIA
Powered by MOMENTUMMEDIA
New AI model to be a force multiplier for network defenders and cyber security professionals.
Google has announced a new security-focused AI model called Sec-Gemini v1, based on its Gemini generative AI chatbot.
The model is still in an experimental phase and is being made available to cyber security researchers, institutions, and non-governmental organisations upon request, for free.
Sec-Gemini v1 combines Gemini’s large language model and threat intelligence from both Google Threat Intelligence and Google-owned cyber security firm Mandiant to deliver threat intelligence in what Google refers to as “near real-time”.
“Defenders face the daunting task of securing against all cyber threats, while attackers need to successfully find and exploit only a single vulnerability,” Google said in a security blog post.
“This fundamental asymmetry has made securing systems extremely difficult, time-consuming and error-prone. AI-powered cyber security workflows have the potential to help shift the balance back to the defenders by force multiplying cybersecurity professionals like never before.”
According to Google, Sec-Gemini v1 beats other AI models in a pair of cyber security benchmarks – CTI-MCQ Cyber security Threat Intelligence and Cyber security Threat Intelligence-Root Cause Mapping – by over 10 per cent.
Google illustrated Sec-Gemini v1’s performance by outlining its in-depth identification of Chinese threat actor Salt Typhoon, which included a full description of the actors tactics and techniques, and the vulnerabilities it was known to exploit. The AI model was also able to outline those vulnerabilities in detail, via integration with Google’s open-source vulnerability database.
“With Sec-Gemini v1, analysts can understand the risk and threat profile associated with specific vulnerabilities faster,” Google said.
Cyber Daily has applied for access to the AI model, so hopefully we can provide some hands-on information on its capabilities in the near future.
David Hollingworth has been writing about technology for over 20 years, and has worked for a range of print and online titles in his career. He is enjoying getting to grips with cyber security, especially when it lets him talk about Lego.
Be the first to hear the latest developments in the cyber industry.
