Google Cloud introduced a new large-language model-powered security platform called Google Cloud Security AI Workbench at the RSA Conference 2023, VentureBeat reports.
Google Cloud Security AI Workbench utilizes the Sec-PaLM LLM, which was created specifically cybersecurity use cases and is able to detect malicious activity and coordinate remediation actions. It processes proprietary threat intelligence data from Google plus frontline intelligence from Mandiant.
The platform comes with VirusTotal Code Insight, a new tool that has just been released via preview, and which enables users to import scripts in order to analyze them for malicious behavior. Another tool, named Mandiant Breach Analytics for Chronicle, enables automatic notifications regarding breaches with aid from Sec-PaLM and is set enter preview in summer 2023.
Imagine a world where you know, as you're generating your infrastructure, theres an auto-generated security policy, security control, or security config that goes along with that, said Google Cloud Vice President of Engineering Eric Doerr. "Thats one example that we're working on that we think will be transformative in the world of security operations and security administration."