--- title: This ‘adversarial’ pattern can prevent surveillance... description: Security researcher Bill Swearingen has developed a reinforcement learning system called noRecognition that generates adversarial patterns capable of defeating... canonical: https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: This ‘adversarial’ pattern can prevent surveillance cameras from detecting you | daily.dev og:description: Security researcher Bill Swearingen has developed a reinforcement learning system called noRecognition that generates adversarial patterns capable of defeating... og:url: https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny og:image: https://api.daily.dev/og/posts/fEASTRtnY.png og:image:alt: This ‘adversarial’ pattern can prevent surveillance cameras from detecting you og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # This ‘adversarial’ pattern can prevent surveillance cameras from detecting you **[TechCrunch](https://daily.dev/sources/tc)** · 6 min read · 0 upvotes · 1 comments ## Summary Security researcher Bill Swearingen has developed a reinforcement learning system called noRecognition that generates adversarial patterns capable of defeating surveillance camera detection algorithms. After 31 million tests, his model can produce patterns that, when printed on clothing or vehicles, prevent detection by 11 open-source algorithms including those powering Flock license plate readers, Axon body cameras, and Clearview AI. The patterns don't block recording but scramble object/face detection. A real-world demo at Def Con 2026 successfully hid a Toyota Yaris from a Flock camera. The project is now crowdfunding merchandise featuring these patterns, with Swearingen keeping the strongest patterns offline to prevent camera makers from countering them. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can adversarial clothing patterns actually defeat license plate readers and facial recognition cameras in real-world tests? Yes, a real-world test at Def Con showed a computer-generated pattern printed on a 2009 Toyota Yaris successfully evaded detection by a Flock license plate reader camera, though the vehicle's wheels remained a challenge to fully obscure. The pattern was created by a reinforcement learning model called noRecognition that defeated all 11 open-source detection algorithms it was trained against, including software behind Flock, Axon body cameras, and Clearview AI. _daily.dev surfaces research like this for developers tracking adversarial ML and computer vision security._ ### How does the noRecognition adversarial pattern generator work technically? It uses a reinforcement learning model that trains itself against open-source video camera detection algorithms, generating patterns and refining them each time a pattern gets detected. Over about a year and 31 million tests, the model progressed from defeating one algorithm at a time to defeating all 11 open-source algorithms tested simultaneously, and now produces new candidate patterns every minute. _engineers exploring adversarial ML techniques can follow this kind of research on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@boltonprestcote** · 0 upvotes > oooo, yes ## Similar posts on daily.dev - [Schneier on Security](https://daily.dev/posts/schneier-on-security-np0vst4mn) · Schneier on Security · 0 upvotes · 0 comments - [Wear Your Way Out Of AI Surveilance](https://daily.dev/posts/wear-your-way-out-of-ai-surveilance-nlk5nscyw) · Hackaday · 0 upvotes · 0 comments --- Tags: [#computer-vision](https://daily.dev/tags/computer-vision), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#facial-recognition](https://daily.dev/tags/facial-recognition) [View this post on daily.dev](https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"This ‘adversarial’ pattern can prevent surveillance cameras from detecting you","url":"https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny"},"datePublished":"2026-08-09T14:02:09.613Z","dateModified":"2026-09-14T09:12:22.155Z","description":"Security researcher Bill Swearingen has developed a reinforcement learning system called noRecognition that generates adversarial patterns capable of defeating...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3cbccf99129c87a79c996fc9d2042e98?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3cbccf99129c87a79c996fc9d2042e98?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"TechCrunch","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"TechCrunch","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tc","url":"https://daily.dev/sources/tc"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"computer-vision,reinforcement-learning,facial-recognition","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"TechCrunch","item":"https://daily.dev/sources/tc"},{"@type":"ListItem","position":3,"name":"This ‘adversarial’ pattern can prevent surveillance cameras from detecting you"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny","comment":[{"@type":"Comment","text":"oooo, yes","datePublished":"2026-08-12T19:14:14.441Z","url":"https://daily.dev/posts/fEASTRtnY#c-bC10dEedS","author":{"@type":"Person","name":"Bolton Prestcote","url":"https://daily.dev/boltonprestcote","image":"https://lh3.googleusercontent.com/a/ACg8ocLYZjj5_addOy0yPKV_nPOcX5AZQ_8-LBi5PS18n9OYcG0qzr8=s96-c"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/this-adversarial-pattern-can-prevent-surveillance-cameras-from-detecting-you-feastrtny#faq","mainEntity":[{"@type":"Question","name":"Can adversarial clothing patterns actually defeat license plate readers and facial recognition cameras in real-world tests?","acceptedAnswer":{"@type":"Answer","text":"Yes, a real-world test at Def Con showed a computer-generated pattern printed on a 2009 Toyota Yaris successfully evaded detection by a Flock license plate reader camera, though the vehicle's wheels remained a challenge to fully obscure. The pattern was created by a reinforcement learning model called noRecognition that defeated all 11 open-source detection algorithms it was trained against, including software behind Flock, Axon body cameras, and Clearview AI. daily.dev surfaces research like this for developers tracking adversarial ML and computer vision security."}},{"@type":"Question","name":"How does the noRecognition adversarial pattern generator work technically?","acceptedAnswer":{"@type":"Answer","text":"It uses a reinforcement learning model that trains itself against open-source video camera detection algorithms, generating patterns and refining them each time a pattern gets detected. Over about a year and 31 million tests, the model progressed from defeating one algorithm at a time to defeating all 11 open-source algorithms tested simultaneously, and now produces new candidate patterns every minute. engineers exploring adversarial ML techniques can follow this kind of research on daily.dev."}}]} ```