""We are now processing every post from the dark web using Gemini, and from there distilling down what threats actually matter," Google Threat Intelligence product manager Brandon Wood stated, emphasizing the tool's focus on relevant threats like data leaks and insider threats."
""We're seeing anywhere from eight to 10 million events a day, and we're able to distill that down in very short throughput," Wood explained, highlighting the efficiency of the Gemini AI in threat analysis."
""Traditional dark-web monitoring tools mostly scrape for key terms and use regex to match those terms, generating between 80 percent and 90 percent false positives," Wood noted, contrasting Gemini's accuracy with conventional methods."
""Within a couple of minutes, we return a profile with a deep understanding of the customer, their environment, their business operations, VIPs, brands, technology," Wood said, describing the rapid profiling capabilities of the service."
Google's Gemini AI agents are designed to monitor the dark web, processing up to 10 million posts daily to identify relevant threats for organizations. The service, now in public preview, utilizes advanced models to create detailed profiles of users' organizations, assessing security risks. Internal tests indicate a 98% accuracy rate in threat identification, significantly reducing false positives compared to traditional monitoring tools. The system generates alerts and classifies potential threats based on a comprehensive understanding of the customer's environment and operations.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]