As Russia prepares its next move, an AI listens to the chatter
A radio broadcast between several Russian soldiers in Ukraine in early March, captured from an unencrypted channel, reveals panicked and confused comrades retreating after coming under artillery fire.
“Vostok, I’m Sneg 02. On the highway we have to turn left, damn it,” one of the soldiers said in Russian, using codenames meaning “East” and “Snow 02.”
“I got it. No need to go any further. Go into defence. Done,” another replies.
Later, a third soldier tries to get in touch with another one with the code name “Sud 95”: “Yug 95, do you have contact with a senior? Warn him of artillery fire from the highway. On the road artillery fire. Don’t go by column. Move carefully.
The third Russian soldier continues, more and more agitated: “Go on the radio. Tell me your situation and the location of the artillery, approximately what weapon they are firing. Later, the third soldier speaks again: “Name your square. Yug 95, answer my questions. Name the name of your square!
While the soldiers spoke, an AI listened. Their words were automatically captured, transcribed, translated and analyzed using several artificial intelligence algorithms developed by Primer, an American company that provides artificial intelligence services to intelligence analysts. While it is unclear whether Ukrainian troops also intercepted the communication, the use of artificial intelligence systems to monitor the Russian military on a large scale shows the growing importance of sophisticated open source intelligence in conflicts. military.
A number of unsecured Russian transmissions were put online, translatedand to analyse on social networks. Other data sources, including smartphone video clips and social media posts, were also examined. But it is the use of natural language processing technology to analyze Russian military communications that is particularly new. For the Ukrainian military, making sense of intercepted communications still typically involves human analysts working in a room somewhere, translating messages and interpreting commands.
The tool developed by Primer also shows how valuable machine learning could become for the analysis of intelligence information. The past decade has seen significant advancements in AI capabilities for image recognition, speech transcript, translation and language processing through large neural network algorithms that learn from large slices of training data. Out-of-the-box code and APIs that use AI can now transcribe speech, identify faces, and perform other tasks, often with great accuracy. Faced with Russia’s numerical and artillery advantages, intercepting communications could well make the difference for Ukrainian troops on the ground.
Primer already sells AI algorithms trained to transcribe and translate phone calls, as well as those that can extract key terms or phrases. Sean Gourley, CEO of Primer, explains that the company’s engineers modified these tools to perform four new tasks: bringing together audio captured from web streams that broadcast communications captured using software emulating the hardware of a radio receiver; to suppress noise, including chatter and background music; transcribe and translate Russian speech; and to highlight key statements relevant to the battlefield situation. In some cases, this involved retraining machine learning models to recognize familiar terms for military vehicles or weapons.
The ability to train and retrain AI models on the fly will become a critical advantage in future wars, Gourley says. He says the company has made the tool available to third parties, but declines to say who. “We won’t say who uses it or what they use it for,” Gourley says. Several other American companies have made available technologies, information and expertise to Ukraine as it fights against the Russian invaders.
The fact that some Russian troops are using unsecured radio channels surprised military analysts. This seems to indicate an underfunded and underprepared operation, says Peter W. Singerlead researcher at think tank New America who specializes in modern warfare. “Russia has used open communications interceptions to target enemies in past conflicts like Chechnya, so they, by all means, should have known about the risks,” Singer said. He adds that these signals could undoubtedly have helped the Ukrainians, although the analysis was most likely done manually. “It indicates communication equipment failures, a certain arrogance and perhaps the level of desperation at the upper levels of the Russian military,” adds mick ryana retired Australian general and author.