AI-Powered Radar Can Now Spy On Your Phone Calls From 10 Feet Away

Oh great, more surveillance!

A team of Penn State computer scientists has cooked up a chilling new way to eavesdrop: detecting the microscopic vibrations your smartphone gives off during a call and translating them into words using artificial intelligence.

The method relies on millimeter-wave radar, the same high-frequency tech powering self-driving car sensors, motion detectors, and 5G networks. Aim it at a phone and it can capture the subtle tremors from the earpiece when someone is speaking. These vibrations are invisible to the naked eye but, with the right tools, can become a transcript of your conversation.

The radar data is run through a modified version of Whisper, an AI speech-recognition model originally designed for clean audio. Instead of retraining the whole system, the team used a low-rank adaptation trick to tweak just 1% of the model’s parameters – enough to boost performance without starting from scratch.

The result? Roughly 60% accuracy on continuous speech from up to 10 feet away, covering a vocabulary of about 10,000 words. It’s not perfect, but it’s plenty to grab key phrases, names, or numbers that could be pieced together to expose private information.

“When we talk on a cellphone, we tend to ignore the vibrations that come through the earpiece and cause the whole phone to vibrate,” said Suryoday Basak, the project’s lead researcher and a doctoral candidate in computer science, adding “If we capture these same vibrations using remote radars and bring in machine learning… we can determine whole conversations.”

This is an evolution of a 2022 project where the same team could only identify 10 pre-set words with 83% accuracy. Now, they’ve moved into the far more complex world of live speech.

As Interesting Engineering notes further; 

Radar tech breakthrough

The experimental setup involved positioning the radar sensor about three meters (10 feet) away from the phone to capture the minute vibrations.

The data was then fed into the customized AI model, which produced transcriptions with around 60 percent accuracy over a vocabulary of up to 10,000 words.

While this is far from perfect, the researchers noted that even partial keyword matches could have serious security implications.

“The result was transcriptions of conversations, with an expectation of some errors, which was a marked improvement from our 2022 version, which outputs only a few words,” said co-author Mahanth Gowda, associate professor of computer science and engineering.

“But even picking up partial matches for speech, such as keywords, are useful in a security context.”

The team compared their approach to lip reading, which typically captures only 30% to 40% of spoken words but can still help people infer conversations when combined with context.

Similarly, the radar-AI system’s output, though imperfect, can reveal sensitive information when supplemented with prior knowledge or manual correction.

Privacy risks amplified

Basak emphasized the potential privacy risks posed by this emerging technology.

“Similar to how lip readers can use limited information to interpret conversations, the output of our model combined with contextual information can allow us to infer parts of a phone conversation from a few meters away,” he said.

“The goal of our work was to explore whether these tools could potentially be used by bad actors to eavesdrop on phone conversations from a distance. Our findings suggest that this is technically feasible under certain conditions, and we hope this raises public awareness so people can be more mindful during sensitive calls.”

The U.S. National Science Foundation supported the research, and the team stressed that their experiments are intended to highlight possible vulnerabilities before malicious actors exploit them.

They envision future efforts to develop protective measures to secure personal conversations from this kind of remote surveillance.

As wireless technology and AI evolve rapidly, this study serves as a crucial warning: even the faintest vibrations from your everyday devices can potentially betray your most private words.

The study has been published in, published in the Proceedings of WiSec 2025: 18th ACM Conference on Security and Privacy in Wireless and Mobile Networks.