{"id":33646,"date":"2023-02-16T16:24:09","date_gmt":"2023-02-16T15:24:09","guid":{"rendered":"https:\/\/alumni.polimi.it\/?p=33646"},"modified":"2024-09-26T14:45:56","modified_gmt":"2024-09-26T12:45:56","slug":"proteggere-i-dati-biometrici-dovremmo-stare-piu-attenti-quando-mostriamo-la-faccia","status":"publish","type":"post","link":"https:\/\/alumni.polimi.it\/en\/2023\/02\/16\/proteggere-i-dati-biometrici-dovremmo-stare-piu-attenti-quando-mostriamo-la-faccia\/","title":{"rendered":"Biometric data, be careful when showing your face online"},"content":{"rendered":"

We stress about refusing the use of cookies, we get angry if a telemarketing company gets our phone number without our knowledge. We see our privacy as important, yet we are not always aware that we are putting it at risk. How many times a day do we step into the view of a surveillance camera<\/strong> without even realising? <\/p>\n\n\n\n

Do we know where our images of us will be collected and stored?<\/strong> Do we know who will use them, and for what purpose? Most of the time, the answer is no. This is the premise behind Rachele Didero\u2019s work, a student designer at the Politecnico di Milano, who has patented Adversarial Knitted Textile. She has come up with a method for putting together pieces of clothing that can protect the wearer against automated facial recognition.<\/strong><\/p>\n\n\n\n

<\/div>\n\n\n\n
\"rachele
Credits: Fondazione CRT<\/a><\/figcaption><\/figure>\n\n\n\n
<\/div>\n\n\n\n

It works thanks to adversarial patterns ('clashing images'): seemingly abstract images that can confuse surveillance camera algorithms. Essentially, if I wear a piece of clothing that is patterned with a clashing image, my biometric facial data cannot be detected, or is placed into an incorrect category, for example in 'animal' instead of 'person', and therefore is not stored. <\/p>\n\n\n\n

The Adversarial Knitted Textile method, patented together with the Politecnico di Milano with the support of Prof. Giovanni Maria Conti, allows the adversarial algorithm to be transferred into a mesh fabric without losing its effectiveness. The patterns confuse facial recognition cameras, thus protecting the person's identity. prof. Giovanni Maria Conti<\/a>allows the adversarial algorithm to be transferred into a mesh fabric without losing its effectiveness. The patterns confuse facial recognition cameras, thus protecting the person's identity. <\/p>\n\n\n\n

<\/div>\n\n\n\n
\n