The airspace management system built on AI and blockchain technologies, SkyGrid, a Boeing, SparkCognition company, is now also one of the first airspace management systems to enable drone protection powered by AI. Together with SparkCognition, an industrial artificial intelligence (AI) company, SkyGrid will deploy AI-powered cybersecurity directly on drones, protecting them from zero-day attacks during flight.
“AI-powered cybersecurity, deployed directly on drones in our system, is critical to protect against malicious activity, such as malware, ransomware, and viruses,” Zehra Akbar, senior director of strategy and operations at SkyGrid, told Commercial UAV News last year. “In the emerging UAV 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, won’t be adequate to detect this unknown malware. Instead of relying on an existing threat database, an AI-based approach can learn the DNA of what a malicious file might look like to detect malicious activity and prevent it from executing on a drone.”
To provide more advanced airspace security than traditional anti-malware, which is reliant on signatures of known threats, and to ensure safer and more secure drone operations in the national and global airspace, SkyGrid’s Aerial OS now integrates SparkCognition’s award-winning DeepArmor AI Endpoint Protection.
“We leveraged cutting-edge AI research and technology to build the DeepArmor product, which allows it to protect endpoints against 99.9% of never-before-seen threats,” said Sridhar Sudarsan, Chief Technology Officer at SparkCognition. “In addition, the product’s uniqueness lies in its ability to provide top-rate endpoint protection on the lowest footprint with minimal interference – all in varying degrees of connectivity. This is the true overarching security differentiator from which SkyGrid’s customers will see value.”
Instead of using signatures, heuristics, or rules-based approaches to detect threats, Aerial OS’ DeepArmor integration uses sophisticated AI models, trained on the DNA of malicious files, to analyze thousands of characteristics of payloads in memory or permanent storage. Not only does this mean the software doesn’t need prior knowledge of a specific threat to detect it and make a classification but, since it is deployed directly on drone hardware, it even works when network connectivity is impaired or non-existent. After identifying a threat, the DeepArmor system intercepts and encrypts the payload in question, automatically puts it in quarantine, and moves it to a secure location for post-flight forensics.
“In the near future, we’ll essentially have a network of flying computers in the sky, and just like the computers we use today, drones can be hacked if not secured properly,” said Amir Husain, CEO and founder of SparkCognition and SkyGrid. “In this emerging environment, traditional anti-malware technology won’t be adequate to detect these never-before-seen attacks. SkyGrid is taking a new, intelligent approach by using AI to more accurately detect and prevent cyberattacks from impacting a drone, a payload, or a ground station.”