A few hours before dawn, under the veil of a new moon, two figures in military fatigues wrestle like Greco-Roman wrestlers within the barbed wire perimeter of the Blue Grass Army Depot in Richmond, Kentucky.
Their movements are rigid but discreet, each maneuvering like a lever under the orange glow of the searchlights lining the security barrier of the depot.
In the distance, a patrolling sentry narrows his eyes, trying to make sense of the dimly lit commotion. He presses the two-way radio on his belt but hesitates, afraid of frustrating his supervisor with an inaccurate report.
But before the fight can unfold – and before the sentry can reassess and call for help – a bright green crosshair highlights the entwined bodies on a control room monitor several miles away. Scylla, the artificial intelligence algorithm that powers the repository’s security architecture, made sense of what the Sentinel cannot understand.
Scylla knows instantly that the image captured by the depot’s security cameras represents a struggle. Within seconds, the algorithm references a database of friendly and malicious faces, identifies the belligerents and sends a report to the watch captain: “An on-duty military police officer attempts to subdue an intruder – a known bad actor with suspected hostile intentions. ”
This fictional scenario described by Drew Walter, Assistant Secretary of Defense for Nuclear Issues, illustrates AI’s demonstrated capabilities and highlights its potential in the realm of physical security. Last month, the Defense Ministry tested Scylla at the Depot. Walter described the platform as “a significant advancement in our ability to protect critical assets.”
“Its ability to learn in real time and reduce false alarms – which fatigue security personnel and prevent responses to legitimate threats – addresses a long-standing challenge in physical security,” he said.
DOD is exploring AI’s ability to enhance existing surveillance and threat detection capabilities, aligning with the department’s broader strategy to integrate data, analytics, and AI across its operations.
The Physical Security Enterprise and Analysis Group, which tests Scylla, plays a central role in the department’s mission to safeguard America’s strategic nuclear capabilities. “PSEAG does physical security well and has taken the reins in both the strategic and conventional domains,” Walter said. “By unifying our disparate efforts under one roof, we can acquire and deploy capabilities that meet the Department of Defense’s nuclear security requirements.”
PSEAG’s interest in AI is part of the ministry’s strategic priorities. Last year, in a speech on “The state of artificial intelligence within the Ministry of Defense“, Kathleen Hicks, Deputy Secretary of Defense, stressed the importance of integrating AI quickly and responsibly.
“While we have focused on integrating AI into our operations responsibly and expeditiously, the primary reason we have done so has been simple: because it improves our decision-making advantage,” said Hicks. “From a deterrence and defense against aggression perspective, AI-based systems can help accelerate commanders’ decision-making and improve the quality and accuracy of those decisions.”
Chris Willoughby, electronic security systems manager at the Depot and project manager for Scylla, is working to bring Hicks’ vision to life. “PSEAG tests, evaluates and trains Scylla’s deep artificial intelligence neural machine learning software to detect and classify person characteristics, behavioral anomalies, threats and armed and unarmed objects by evaluating video surveillance systems in real time,” he said.
The demonstration at the Depot showcased Scylla’s ability to detect intruders, weapons and abnormal behavior using existing video surveillance systems and drones. In one case, the software identified an armed individual climbing a water tower a mile away. “Scylla testing and evaluation has demonstrated detection probability above 96% of accuracy standards, significantly reducing false alarm rates due to environmental phenomena,” Willoughby said.
Walter echoed Willoughby’s enthusiasm, praising Scylla’s unique and cost-effective application to existing physical security architecture. “Scylla AI leverages any suitable video feed available to monitor, learn and alert in an instant, reducing the operational burden on security personnel,” he said. “While humans still make the final decisions about responding to threats, AI is increasing detection capabilities.”
Walter said Scylla’s most vital application may lie in improving the physical security of the DOD’s strategic nuclear arsenal. “Scylla’s transformative potential lies in its support of PSEAG’s core mission, which is to safeguard U.S. strategic nuclear capabilities while in the department’s custody,” he said. “The ability to quickly detect and respond to threats is paramount when dealing with critical deterrence assets, whether Trident missile submarines, intercontinental ballistic missiles or strategic bombers. ”
Beyond the Depot, the department is exploring the potential of Scylla in cold weather and maritime environments. In the coming months, Joint Base Charleston, South Carolina, will conduct evaluations led by the Navy and Marine Corps, ensuring the algorithm meets the specific demands of their services.
PSEAG officials said they were particularly interested in testing AI’s ability to mitigate an emerging threat: unmanned systems capable of transcending domains by emerging from the sea to operate on land or in the air.
Although it faces challenges in the form of new threats, conditions and environments, Walter and Hicks said AI is essential to maintaining the United States’ competitive technological advantage.
The deputy secretary said the department has worked for more than a decade to become a global leader in the development and use of AI technologies. “By putting our values first and building on our strengths – the most important of which is our people – we have taken a responsible approach (to artificial intelligence) that will ensure America continues to lead. ”
PSEAG’s investment in AI comes from 2022 National Defense StrategyThe commitment to “spur commercialization…of emerging technologies,” such as “artificial intelligence and autonomy,” and the algorithm’s remarkable performance in Richmond, Ky., mark a fundamental step on the department’s path towards improved physical security and full adoption of AI.
“By adopting advanced technologies, like Scylla, we are not only improving our current security measures,” Walter said, “we are laying the foundation for future innovations that will keep our nation safe.”