conv.

All stories
SecurityRunning 6h

Bill Swearingen's noRecognition defeats surveillance camera detection

Security researcher demonstrates computer-generated patterns that prevent license plate readers and facial recognition from detecting people and vehicles.

Conversation activity · last 24 hours peak 5/hr

Peak 5 items in one hour at Aug 9, 9 AM; 12 items over 24 hours Aug 8, 9 PM — no itemsAug 8, 10 PM — no itemsAug 8, 11 PM — no itemsAug 9, 12 AM — no itemsAug 9, 1 AM — no itemsAug 9, 2 AM — no itemsAug 9, 3 AM — no itemsAug 9, 4 AM — no itemsAug 9, 5 AM — no itemsAug 9, 6 AM — no itemsAug 9, 7 AM — no itemsAug 9, 8 AM — no itemsAug 9, 9 AM — 5 itemsAug 9, 10 AM — 1 itemAug 9, 11 AM — no itemsAug 9, 12 PM — 1 itemAug 9, 1 PM — 3 itemsAug 9, 2 PM — 1 itemAug 9, 3 PM — 1 itemAug 9, 4 PM — no itemsAug 9, 5 PM — no itemsAug 9, 6 PM — no itemsAug 9, 7 PM — no itemsAug 9, 8 PM — no items 5 items · 9 AM
Aug 9

Summary, timeline and people extracted by Claude from 12 items across 4 sources · 6h ago. Quotes are verbatim.

Bill Swearingen, a cybersecurity professional from Kansas City, has developed noRecognition, a system that generates adversarial patterns capable of preventing surveillance cameras and license plate readers from detecting people, faces, and vehicles. After running 31 million tests over a year, Swearingen successfully demonstrated the pattern on a vehicle at DEF CON in Las Vegas, proving it can defeat detection algorithms in real-world conditions. Swearingen frames the work as enabling people to opt out of ubiquitous tracking and protect constitutional rights to free expression without surveillance.

  • Bill Swearingen developed noRecognition, a system generating adversarial patterns that defeat surveillance camera detection algorithms after 31 million tests over one year.
  • The patterns scramble detection without blocking video recording, allowing people and vehicles to evade automatic identification by license plate readers and facial recognition systems.
  • Swearingen frames the technology as enabling constitutional privacy rights and protection from chilling effects of surveillance on free expression.
  • The system was successfully demonstrated at DEF CON in Las Vegas on a vehicle, proving effectiveness in real-world conditions.

How it unfolded

  1. Reaction Social media amplification begins

    The story spread across Bluesky, Mastodon, and Google News, with cybersecurity and surveillance-focused accounts sharing and discussing the technical achievement.

  2. Report TechCrunch article published

    TechCrunch reporter Zack Whittaker published detailed coverage of Swearingen's noRecognition project, explaining how the patterns scramble camera detection without blocking video recording.

  3. 8 days quiet
  4. Event Completed 31 million algorithmic tests

    After running the same test repeatedly over a year, Swearingen achieved the ability to produce adversarial patterns on-demand that prevent detection by commonly deployed surveillance cameras and license plate readers.

  5. Event DEF CON public demonstration

    Swearingen successfully demonstrated his adversarial pattern printed on a vehicle at the DEF CON cybersecurity conference in Las Vegas, proving the patterns work in real-world surveillance conditions.

    “Privacy is a fundamental right. He described his patterns as a way to allow people to "opt-out of being tracked."”

    Bill Swearingen · Mastodon ↗
  6. 52 weeks quiet
  7. Event Swearingen began noRecognition project

    Bill Swearingen initiated a year-long effort to develop computer-generated patterns that could defeat surveillance detection algorithms, motivated by concerns about camera density in his town and surveillance chilling effects on protest attendance.

What people are saying verbatim

“Privacy is a fundamental right. He described his patterns as a way to allow people to "opt-out of being tracked."”

Bill Swearingen, Security researcher, noRecognition developer · TechCrunch ↗ · Aug 8

“Swearingen's computer-generated patterns do not block surveillance cameras from recording video footage. Instead, they scramble the camera's ability to identify objects, people, or faces, so that the cameras do not trigger any detection alerts.”

TechCrunch, Reporter · TechCrunch ↗ · Aug 8

“By blocking the camera's ability to detect what the pattern covers, the person becomes a needle in a haystack again — until someone knows where to look.”

TechCrunch, Reporter · TechCrunch ↗ · Aug 8

“He said that he and others never opted in to being watched, just like he never opted-in to having the government use his driver's license for facial recognition.”

Bill Swearingen, Security researcher · TechCrunch ↗ · Aug 8