The tactics of warfare aren’t what they used to be. In addition to asymmetric battlefield tactics that differ from conventional battles, they also can include cyber, social, economic, and psychological strategies that don’t necessarily involve physical combat or destruction–or even direct human involvement–and can’t be divined by tracking troop movements or fleet deployments. As a result, the signs of impending war aren’t what they used to be either.

The Pentagon wants to develop a way to detect those signs by analyzing the myriad actions in what it calls the “gray zone”–behaviors in a variety of areas that, considered separately, may or may not mean anything but when examined together could indicate malicious intent–and is putting artificial intelligence (AI) to work on the problem.

The Defense Advanced Research Projects Agency (DARPA) has launched a new program intended to better understand and interpret an adversary’s gray zone engagement as potential signals of pending aggression. The Collection and Monitoring via Planning for Active Situational Scenarios (COMPASS) program will incorporate AI, game theory, modeling, and estimation technologies to decipher the often subtle signs that precede a full-scale attack.

“The ultimate goal of the program is to provide theater-level operations and planning staffs with robust analytics and decision-support tools that reduce ambiguity of adversarial actors and their objectives,” said Fotis Barlos, DARPA program manager. “As we see increasingly more sophistication in gray zone activity around the world, we need to leverage advanced AI and other technologies to help commanders make more effective decisions to thwart an enemy’s complex, multi-layered disruptive activity.”

The attention to gray zone activity reflects the multi-pronged tactics used in hybrid warfare, of the type employed by Russia in Georgia in 2008 and in Ukraine since 2014. Cyber attacks to shut down the power grid, conduct digital espionage, and sow economic disruption, along with social media campaigns aimed at manipulating public opinion, coincided with the covert movement of troops and equipment into Ukraine. Not only have these tactics proved to be effective, their subtle, sometimes untraceable methods can lend a level of plausible deniability to the attacks. And NATO has said that clandestine hybrid attacks can achieve their aims before being noticed, too late for an effective response.

Hybrid attacks disrupt the military’s OODA (Observe, Orient, Decide and Act) loop, which has long served as a reliable way to anticipate and plan for attacks in places around the world. COMPASS would add a “dynamic, adaptive element” to assist military decision-makers in complicated, gray zone environments, DARPA said. It will use advanced software to analyze incoming data and give commanders options, using game theory to simulate and test possible actions and reactions.

“We’re looking at the problem from two perspectives. Trying to determine what the adversary is trying to do, his intent; and once we understand that or have a better understanding of it, then identify how he’s going to carry out his plans,” Barlos said. “So it is using artificial intelligence in a repeated game theory process to try to decide what the most effective action is based on what the adversary cares about.”

COMPASS will support the military’s plans for preparing for hybrid warfare, which the Army also refers to as  Multi-Domain Battle. DARPA will hold a Proposer’s Day on March 30 in Arlington, Virginia, looking for experts in AI, game theory, and other contributing technologies.

Read More About
More Topics