Laboratory thwarts insider threat with Darktrace AI

Posted on 21 March, 2022 by Advance 

A leading laboratory specialising in vitro diagnostics has successfully stopped an insider threat with the help of Darktrace's self-learning AI.

Image courtesy Darktrace

The company, which has laboratories, offices and distribution centres in over 100 countries worldwide and more than 3,000 employees, specialises in the research, development and manufacturing of innovative in vitro diagnostic tests for disease, conditions and infections. The organisation uses Darktrace's detect, respond and investigate capabilities to defend against in-progress attacks at the early-stages.

Powered by Self-Learning AI, Darktrace technology develops an understanding of normal operations for the company. From this understanding it can then autonomously interrupt in-progress attacks at every stage from the initial entry with sophisticated spearphishing emails to brute-forced remote desktop protocol (RDP), command-and-control, and lateral movement, all without business disruption.

In one instance, Darktrace's Self-Learning AI detected an internal device communicating with the Tor network via an intermediary web service. Tor is an open-source privacy network that enables anonymous web browsing by guiding data traffic through different servers, located all over the world. Whilst it is not wholly malicious, it can be associated with the browsing of non-business or even illegal content.

The device was connecting with a darknet forum relating to the pharmaceutical market. Given that no other device within the organisation had visited the Tor network in the past, Darktrace AI flagged this to the security team as out-of-the-ordinary. With the AI taking care of early detection and making micro-level decisions the security team were uplifted and able to make important decisions that required business context.

The internal security team later found that this was likely an insider looking to sell proprietary intellectual property or even medical supplies on the darknet.

"Malicious or compromised insiders can be difficult to identify because their privileged access and knowledge of company workings allows them to evade detection by traditional security tools," commented Toby Lewis, Global Head of Threat Analysis, Darktrace. "In order to protect intellectual property from insider threat, organizations need to augment security teams with AI-powered technology to stop malicious activity in real time at the moment of detection."