A few hours before dawn, under the veil of a new moon, two figures in military uniform grapple like Greco-Roman wrestlers around razor wire at the Blue Grass Army Depot in Richmond, Kentucky.
Their movements are rigid but deliberate, each maneuvering with strength under the orange light of floodlights lining the warehouse’s security fence.
A sentry patrolling in the distance squints, trying hard to make sense of the dim commotion. He thumbed the two-way radio on his pistol belt, but hesitated, worried he would irritate his superiors with inaccurate reports.
But before the battle moves to the ground, and before the sentries can reassess and call for support, a bright green reticle highlights tangled bodies on a control room monitor miles away. Scylla, the artificial intelligence algorithm that powers the depot’s security architecture, understood something the sentries didn’t.
Scylla instantly realized that the images captured by the warehouse’s surveillance cameras depicted a struggle. In seconds, the algorithm consults a database of friendly and malicious faces to identify the belligerent, allowing military police on duty to attempt to subdue the intruder, a known bad guy who is presumed to be hostile. I will report that there is. ”
This hypothetical scenario described by Drew Walter, Deputy Assistant Secretary of Defense for Nuclear Affairs, illustrates the proven capabilities of AI and highlights its potential in the realm of physical security. Last month, the Pentagon tested Scylla at a supply 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 nuisance alarms that fatigue security personnel and prevent them from responding to legitimate threats addresses a long-standing challenge in physical security,” he said.
The Department of Defense is focused on AI’s ability to enhance existing surveillance capabilities and threat detection, in line with the department’s broader strategy to integrate data, analytics, and AI across its operations.
The physical security companies and analysis groups conducting the Scylla test play a vital role in the department’s mission to protect America’s strategic nuclear capabilities. “PSEAG does physical security well and takes the reins in both the strategic and traditional areas,” Walter said. “By integrating disparate efforts under one umbrella, we can procure and field capabilities that meet the Department of Defense’s nuclear security requirements.”
PSEAG’s interest in AI is embedded in the department’s strategic priorities. Last year, Deputy Secretary of Defense Kathleen Hicks emphasized the importance of integrating AI quickly and responsibly in a speech on “The State of Artificial Intelligence in the Department of Defense.”
“We have been focused on integrating AI into our operations responsibly and quickly, and the primary reason for doing so is straightforward: it improves decision-making,” Hicks said. Masu. “From the perspective of deterring and defending against aggression, AI-enabled systems can help commanders accelerate the speed of decision-making and improve the quality and accuracy of those decisions.”
Chris Willoughby, the depot’s electronic security systems manager and Scylla’s project leader, is working to bring Hicks’ vision to life. “PSEAG uses Scylla’s artificial intelligence deep neural machine learning software to detect and classify human characteristics, behavioral anomalies, armed and unarmed threats and objects by evaluating video surveillance systems in real time,” he said. “We are testing, evaluating and training.”
The demonstration at the depot demonstrated Scylla’s ability to detect intruders, weapons, and unusual behavior using existing video surveillance systems and drones. In one example, the software identified an armed individual climbing a water tower a mile away. “Scylla testing and evaluation demonstrated a detection probability that exceeded the 96% accuracy standard and significantly reduced 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 architectures. “Scylla AI leverages any relevant video feed available to instantly monitor, learn, and alert, reducing operational burden for security personnel,” he said. “While humans still make the final decision on how to respond to threats, AI is enhancing detection capabilities.”
Walter said Scylla’s most important use may be in improving the physical security of the Pentagon’s strategic nuclear weapons. “Scylla’s transformative potential lies in its support of PSEAG’s core mission of protecting America’s strategic nuclear capabilities when they are under the department’s control,” he said. “When dealing with assets critical to deterrence, whether it’s a Trident missile submarine, an intercontinental ballistic missile, or a strategic bomber, the ability to rapidly detect and respond to threats is paramount.”
Beyond warehouses, the department is also researching Scylla’s potential in cold regions and marine environments. A Navy and Marine Corps-led evaluation will be held at Joint Base Charleston, South Carolina, in the coming months to ensure the algorithms meet mission-specific requirements.
PSEAG officials said they are particularly interested in testing AI’s ability to mitigate emerging threats. It is an unmanned system that can emerge from the sea and operate across domains, on land and in the air.
In the face of new threats, situations, and environmental challenges, Walter and Hicks said AI is essential to maintaining America’s technological competitiveness.
He said the department has been working for more than a decade to become a global leader in the development and use of AI technology. “By putting our values first and maximizing our strengths, our greatest strength is our people. We will take a responsible approach to (artificial intelligence) and ensure that the United States continues to I guarantee you will have an advantage.”
PSEAG’s AI investment stems from the 2022 National Defense Strategy’s commitment to “advance the commercialization of emerging technologies” such as “artificial intelligence and autonomy,” and highlights the algorithm’s work in Richmond, Kentucky. The performance represents a fundamental milestone on the path to the Department’s goals. Improving physical security and deploying comprehensive AI.
“By employing advanced technologies like Scylla, we are not only strengthening current security measures, but also laying the foundation for future innovations that will protect our national security,” Walter said.
