tech
This 'adversarial' pattern can prevent surveillance cameras from detecting you
A security researcher has designed an algorithm that can create computer-generated patterns capable of hiding people, faces, and vehicles from detection by surveillance cameras.
TL;DR
- Bill Swearingen developed the noRecognition project to create patterns that block surveillance camera detection.
- These patterns scramble the camera's ability to identify objects, people, or faces, preventing detection alerts.
- Swearingen's system uses a reinforcement learning model that continuously refines patterns to defeat various detection algorithms.
- The patterns have proven effective against common surveillance technologies, including Flock license plate readers and Axon body-worn cameras.
- A public demonstration at the Def Con cybersecurity conference successfully used a pattern to make a vehicle less detectable by a Flock camera.
- The project is seeking funding through a crowdsourcing campaign for merchandise featuring the patterns.