Latest news with #WiSec2025
Hans India
a day ago
- Science
- Hans India
New AI Hack Uses Radar to Eavesdrop on Phone Calls from 10 Feet Away
Artificial intelligence continues to be a double-edged sword—unlocking revolutionary possibilities on one hand, while raising serious security threats on the other. A new study by researchers at Penn State University has now brought to light an unsettling development: an AI-powered wireless-tapping system capable of eavesdropping on private phone conversations from as far as 10 feet away. The research was presented at the 18th ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec 2025) and has since stirred concerns about the future of privacy in an AI-driven world. How the system works The experimental setup, described as 'wireless-tapping,' uses radar signals to detect the minute vibrations produced by a smartphone's earpiece during a phone call. These vibrations, though imperceptible to the human eye or ear, carry enough information for AI models to reconstruct parts of the spoken conversation. 'Whenever we talk on the phone, a caller's voice is played through the earpiece speaker, creating tiny vibrations across the phone's surface. If we capture these same vibrations using remote radars and bring in machine learning to help us learn what is being said, we can determine whole conversations,' explained Suryoday Basak, a doctoral researcher at Penn State's College of Engineering. The team used a millimetre-wave radar sensor—commonly found in 5G networks, motion detectors, and self-driving cars—to capture these subtle surface movements. Positioned a few meters away from the target device, the radar was able to pick up vibration data, which was then processed using an AI tool. Whisper AI with a twist For speech recognition, the researchers turned to Whisper, an open-source AI model created by OpenAI. Instead of retraining the entire model, they applied a technique known as low-rank adaptation, tweaking just 1 percent of Whisper's parameters. This adjustment enabled the AI to make sense of noisy, radar-based input, which differs significantly from the clean audio Whisper is typically trained on. The results, while not flawless, were startling. The AI system successfully reconstructed phone call transcripts with about 60 percent accuracy when tested against a vocabulary set of 10,000 words. While incomplete, these transcripts were detailed enough to capture identifiable phrases, raising serious questions about potential misuse. Privacy risks and the road ahead Though the Penn State team emphasized that their project was created purely for academic exploration, the implications are clear. As radar sensors become smaller and more affordable, and AI transcription tools continue to advance, the risk of covert wireless spying grows exponentially. The researchers even pointed out that radar chips could eventually be embedded into everyday objects—like pens, smart home devices, or office gadgets—making hidden surveillance far easier to deploy. While the current technology is still experimental and not yet practical for widespread use, this study serves as a wake-up call. As AI continues to intersect with emerging sensor technologies, the need for stronger privacy protections and awareness has never been more urgent.
India Today
a day ago
- India Today
New AI hack can eavesdrop on your phone calls from 10 feet away using radar signals
AI is both a boon and a bane. On one hand, it is opening doors to groundbreaking technologies, while on the other, it is exposing us to new risks. Researchers at Penn State in the US have identified one such risk. They have experimented with an AI-powered system that can eavesdrop on phone calls, even when you are several feet away. And the result has now raised new concerns over study was presented at the 18th ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec 2025) (Via Penn State blog post). In the study researchers detailed how they used artificial intelligence and radar technology to intercept private phone conversations without ever touching the device. The research team tested a system they call 'wireless-tapping', which shows that phone conversations can be partially transcribed from up to 10 feet away by measuring the tiny vibrations generated by a smartphone's earpiece. According to the researchers, while the call-tapping technology is still in its early stages, their experiment demonstrated that transcripts could be reconstructed with around 60 per cent accuracy when using a vocabulary of up to 10,000 wireless-tapping using AI works So how does this AI system work? Well according to researchers, whenever we talk on the phone, a caller's voice is played through the earpiece speaker, creating tiny vibrations across the phone's surface. Ordinarily, these vibrations go unnoticed. But in this experiment, the researchers managed to decipher the call using these vibrations. 'If we capture these same vibrations using remote radars and bring in machine learning to help us learn what is being said, we can determine whole conversations,' said Suryoday Basak, a doctoral researcher at Penn State's College of researchers used a millimetre-wave radar sensor, the same technology found in self-driving cars, motion detectors and 5G networks. They positioned it a few metres away from a smartphone. During the experiment, the radar managed to detect subtle surface movements caused by the earpiece on the smartphone. The researchers then processed these vibration signals using a customised version of Whisper, an open-source AI speech recognition model developed by instead of retraining the entire model, the researchers reportedly applied a technique called low-rank adaptation, which allowed them to adjust only about 1 per cent of Whisper's parameters. This helped the AI system interpret 'noisy' radar data, which looks very different from the clean audio Whisper is usually trained the results of this experiment were concerning. The system was able to produce partial but recognisable transcripts of phone conversations. While far from perfect, the output was reportedly detailed enough to identify key phrases, raising fears that similar techniques could be exploited for researchers highlight that their system was built strictly for academic purposes and is not a ready-made spying tool. However, they cautioned that the miniaturisation of radar sensors, coupled with rapid advances in AI speech recognition, could make it feasible for people to replicate the technology in compact, hidden fact, the team noted that radar chips can already be shrunk into everyday objects, such as pens or smart home gadgets, making discreet wireless eavesdropping a very real possibility in the near future. - Ends
