In a press release, ZingBox said the self-learning approach to the tool enables it to continually build upon previous knowledge to discover, detect and defend critical IoT services and data, all the while avoiding false positives with what the company said is 99.9 percent accuracy.
“Enterprises, health care organizations and manufacturing floors are embracing the digital age with a wide variety of connected devices to improve productivity, decision making and service delivery. But the resulting Internet of Things is highly vulnerable and lacks a crucial component: trust,” said Xu Zou, cofounder and CEO of ZingBox, in the press release. “ZingBox is first to provide a solution based on deep learning that recognizes each device’s personality to enable what customers demand: the Internet of Trusted Things.”
According to ZingBox, traditional IT security relies on detecting malware based on a few well-understood platforms, but the solutions can’t defend a diverse set of IoT devices that often run on customized operating systems. To instill trust in the device, ZingBox said it came up with the new approach to security. ZingBox said the device personality approach was first conceptualized at Stanford University by ZingBox founders.
“Medical device networks in a hospital are not rigorously monitored. We needed a solution that would generate a real-time inventory of medical devices across the hospital network and evaluate the risk exposure,” said Jerry Marshall, director of information services and telecommunications at United Regional Health Care System, in the same press release. “The ZingBox solution discovered over 95 percent of medical devices compared to current tools that could only detect about 5 percent. The intelligence and accuracy of elaborate device personalities allowed us to turn ZingBox into a tool that regulates medical device behaviors.”
We’re always on the lookout for opportunities to partner with innovators and disruptors.
Learn More