Images courtesy of SkyGrid
The Federal Aviation Administration (FAA) predicts the future of commercial UAS fleet by 2025
From autonomous drones to air taxis, the urban air mobility market has advanced rapidly over the last two to three years. These drones are performing real commercial tasks – they are delivering packages, conducting industrial inspections, providing emergency assistance, and will eventually transport people.
Based on the latest data, the Federal Aviation Administration (FAA) predicts the commercial UAS fleet by 2025 will likely number 835,000 vehicles. 1.7 times larger than the current number of commercial sUAS. More drones are expected to take flight in coming years spanning a wide range of civilian and commercial use cases, but all this comes with as-yet unaddressed challenges. Drone data integrity, maintenance, and drone deconfliction need to be addressed. These issues range in severity from inconvenient to dangerous. On the one hand, significant growth in drone numbers and capability is incredibly exciting, however, this also presents a major challenge in terms of effectively protecting aircraft systems from being attacked by zero-day cybersecurity threats remotely.
Preventing Malicious Activity with AI-Powered Cybersecurity
With the rise of communication between people and devices and the rise of computing performance, aircraft such as drones are not immune to cybersecurity risks that have become prevalent and critical issues for other industries. Large numbers of airborne drones are essentially a network of flying computers in the sky. Just like the computers we use today, these drones can be hacked if not secured properly, posing dangers when they are flying close to a crowd of people or a busy highway.
In this emerging environment, new security threats will often take the form of previously unseen, “zero-day” attacks. Traditional anti-malware software, dependent on signatures of known threats, will not be adequate to detect such sophisticated, new malware.
Images courtesy of SkyGrid
AI-powered cybersecurity holds the key to detecting malicious activity on the edge and preventing it from making its way on to a drone or executing on its computer systems. An AI-based approach can learn the DNA – the structure – of what a malicious file might look like instead of merely relying on an existing threat database. This type of technology can function even when network connectivity is non-existent or impaired and can defend drones against zero-day threats. AI-powered cybersecurity will be key in ensuring public safety by providing an adaptable system that protects against never-before-seen attacks.
Leveraging machine learning technology combined with a “defense in depth” approach can provide multiple layers of protection for an endpoint. Cognitive cybersecurity solutions enable more advanced airspace security than traditional antimalware systems which remain reliant on signatures of known threats. In contrast to known signatures, heuristics, or other dated rules-based approaches to detect security threats, the DeepArmor® product uses patented machine learning technology and a layered protection strategy to protect a drone’s endpoints. Not only can DeepArmor® protect drones from known threats, its machine-learning detection engine also uses advanced classification algorithms to predict and prevent zero-day attacks, enhancing protection.
A New Era of Protection for Drones in Defense
DeepArmor® is already proven and effective in the commercial sector. Now, the technology can be extended for use on UAVs within the defense industry to counter national security threats. Considering emerging threats as seen in the capture of the RQ170 by Iran are now a fact of life, an AI-based approach is critical to detect and prevent such cyberattacks. The DeepArmor® Aerial product can provide this detection and protection by deploying directly on drone hardware even when network connectivity is impaired or non-existent.
Boeing and SparkCognition’s joint venture, SkyGrid, is taking this new, intelligent approach to security by employing AI to detect and prevent cyberattacks from impacting a drone, a payload, or a ground station. Integrated with SkyGrid’s airspace management system, AerialOS™, the DeepArmor® product can be deployed directly on drone hardware to extend AI protection and defend drones from sophisticated cyber attacks.