Bill Swearingen, a cybersecurity professional from Kansas City, has developed noRecognition, a project that generates computer patterns capable of blocking detection by surveillance cameras and license plate readers.

After running approximately 31 million tests, Swearingen’s reinforcement learning model can now produce patterns on demand that defeat 11 open-source detection algorithms, including those used by Flock license plate readers, Axon body cameras, and Clearview AI.

The patterns do not block video recording but scramble the camera’s ability to identify objects or people, preventing detection alerts. Swearingen describes this as a way for individuals to “opt-out of being tracked,” citing privacy as a fundamental right.

At the Def Con cybersecurity conference in Las Vegas, a public test demonstrated the pattern’s effectiveness on a vehicle, marking early proof that algorithmic detection can be avoided in real-world settings. The project is now seeking crowdfunding to produce merchandise featuring the patterns.

Disclaimer: This post is for informational purposes only and is based on publicly available reports. The image is AI generated and is just for reference.
#Cybersecurity, #Surveillance, #Privacy, #DefCon, #AI