Aperio Systems, unveiled today, is offering its customers a “polygraph for process data, detecting when your system is lying to you”, CEO Yevgeni Nogin told Forbes in a recent interview.
“We have an unusual number of physicists on board, in addition to cybersecurity experts” – Yevgeni Nogin
Aperio is basically a clever answer to the recent increase in attacks on infrastructure systems, Forbes writes, listing incidents such as a Ukrainian power grid being taken down, leaving more than 230,000 residents without electricity, and a few months later, hackers managed to infiltrate a water treatment plant in the U.S, changing the levels of chemicals being used to treat tap water.
However, “the vast majority of attacks are not disclosed,” Michael Shalyt, VP of Product at Aperio said. “Hackers have realised recently that they can attack the physical world using digital code”. Forbes writes that the Internet of Things (IoT) is to blame for the merge of physical and digital data and the inadequate security of physical objects.
This became very apparent last month when the Internet in parts of the U.S. was shut down due to an attack constructed by taking control over insecure connected devices, such as security cameras and baby monitors. Similar attacks are now threatening the sensors and other physical objects, such as power plants and other industrial control systems, which is a severe problem.
This is where Aperio comes in, addressing the challenge by non-intrusively entering an existing system and unleashing its advanced machine learning algorithms in order to study and identify the system’s unique “fingerprints”.
“That serves as the baseline for determining the validity of the process data produced at any given moment and alerting operators when an anomaly—forged data—is detected. The attackers typically produce forged data because they need to mask their presence and gain the time required for them to inflict long-term damage to the equipment”, Forbes explains.
“Our role is to understand the process well enough that whenever an attacker will send a signal that cannot be generated by this specific equipment or plant or mode of operation, we alert the operators that someone is fooling them,” Shalyt told the newspaper.
By applying a sophisticated combination of physics and state-of-the-art machine learning techniques, Aperio is able to reconstruct the real values of the forged operational data, and then reverting it back to its original state in real time. Establishing the true state of the system is essential in order to determine whether or not there is a need for an emergency shutdown of a system, or rather doing a more controlled one that is less expensive and disruptive.
This article was first published at: http://www.forbes.com/sites/gilpress/2016/11/15/artificial-intelligence-lie-detector-to-protect-critical-infrastructure/#6c41c7e01b52