KAIST Develops SweepLED to Detect Hidden Cameras in 5 Seconds Using AI and 10,000 Won LED

Conventional portable detectors require the user to visually identify bright spots of reflected light from a lens after illumination, which often leads to misidentification with reflections from metal, glass, or glossy plastics. SweepLED continuously changes the direction of the LED light while keeping the smartphone camera fixed, capturing changes in reflection on the object's surface. While reflections from typical glossy objects move or disappear as the light direction changes, camera lenses exhibit unique reflection patterns when illuminated from different angles due to their internal multi-layered structure. Deep learning is used to analyze the position and shape of these time-varying reflections to determine if they originate from a camera lens.

In experiments using 30 types of common household objects—such as chargers, alarm clocks, remote controls, and ornaments—the system achieved a detection accuracy of 94%, with each inspection taking less than 5 seconds. The core components of the LED device cost approximately $7 (about 10,000 won), and the research team stated that it can be deployed as a low-cost hidden camera detector that general consumers can carry and use like a smartphone accessory.

Professor Jun Han said, "Illegal hidden cameras pose a serious threat to individual safety and privacy in everyday spaces," and added that "by combining low-cost hardware with AI analysis, we have demonstrated the possibility of detection technology that can be easily used even by non-experts."