Latest news with #SuryodayBasak
Yahoo
2 days ago
- Science
- Yahoo
AI-powered radar can spy on phone calls from 10 feet, exposing new privacy risks
Believe it or not, your phone's tiniest vibrations can reveal your conversations — thanks to AI. A team of computer science researchers at Penn State has developed a startling new way to eavesdrop on phone calls remotely by decoding subtle vibrations emitted by a cellphone's earpiece. Using millimeter-wave radar combined with an AI speech recognition system, their setup can capture and transcribe conversations from up to 10 feet away with about 60% accuracy. This breakthrough raises significant privacy concerns about the potential misuse of such emerging technologies. The research builds on a 2022 project where the team achieved up to 83% accuracy in recognizing 10 predefined words using a similar approach. The new work extends this capability to continuous speech transcription, though the accuracy is lower due to the complexity of decoding noisy radar data. '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 first author Suryoday Basak, a doctoral candidate in computer science. 'If we capture these same vibrations using remote radars and bring in machine learning to help us learn what is being said, using context clues, we can determine whole conversations. By understanding what is possible, we can help the public be aware of the potential risks.' The team used a millimeter-wave radar sensor, the same technology employed in self-driving cars, motion detectors, and 5G wireless networks, to measure the tiny surface vibrations generated by speech played through a phone earpiece. To interpret this noisy and low-quality data, they adapted Whisper, an open-source AI speech recognition model developed for clean audio, using a low-rank adaptation machine learning technique. This method allowed them to retrain just 1 percent of Whisper's parameters specifically for radar data, improving transcription results without rebuilding the entire model from scratch. 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. Solve the daily Crossword
India.com
3 days ago
- India.com
From 10 feet away, AI can now listen to your phone calls using..., researchers say their goal is to make people...; Is our privacy in danger?
There are many software tools around in the world that can detect what people are talking about on the phone. Cases of phone tapping are common, and the Pegasus spyware controversy made headlines a few years ago. But now, technology has advanced so much that you don't even need spyware to listen to someone's phone conversation. With the help of AI, conversations can be picked up from as far as 10 feet away—just by detecting the vibrations from the phone. This has raised serious concerns about privacy. Millimeter-wave radar and AI make it possible According to a report by Interesting Engineering , researchers at Penn State University's computer science department have found a surprising new way to eavesdrop on phone calls. They used millimeter-wave radar along with artificial intelligence to detect tiny vibrations coming from a phone's earpiece and convert them into speech. This technology can track conversations from 10 feet away with about 60 per cent accuracy. Millimeter-wave radar turning vibrations into words The researchers used millimeter-wave radar, the same type of technology used in self-driving cars, motion sensors, and 5G networks. When we talk on the phone, the sound from the earpiece causes tiny vibrations in the phone's body. This radar can detect those vibrations. With the help of AI, the vibrations are then analyzed and converted into text. Researcher Suryoday Basak explained that by capturing these vibrations with radar and using machine learning, it's possible to figure out the conversation. While the technology isn't 100 per cent accurate yet, it is accurate enough to leak sensitive information. 60 per cent of the conversation was correct In their trials, researchers placed the radar about 3 meters (roughly 10 feet) away from the phone. From this distance, the radar detected tiny vibrations from the phone, and AI converted the data into about 10,000 words of text. Around 60 per cent of the conversation matched accurately. While it's not fully precise yet, if this technology improves in the future, it could become a serious threat to privacy. Big privacy concerns This development has sparked serious privacy questions. Researcher Suryoday Basak explained that it works a bit like lip reading, just as lip readers can guess what's being said, this system can do the same with vibrations. The real danger comes if someone with bad intentions uses it. The researchers say their goal is to make people aware of the risk so they can be more careful during sensitive conversations.
