SecTools Podcast E21 With Emily Wenger
11 ago 2020 ·
27 min. 23 sec.
![SecTools Podcast E21 With Emily Wenger](https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_480/images.spreaker.com/original/79076a54b69655d2a6e95a946d1ca6d0.jpg)
Scarica e ascolta ovunque
Scarica i tuoi episodi preferiti e goditi l'ascolto, ovunque tu sia! Iscriviti o accedi ora per ascoltare offline.
Descrizione
Emily Wenger is a PhD student at the University of Chicago studying machine learning security and privacy. She’s particularly interested in understanding and preventing the unintended uses/abuses of facial recognition...
mostra di più
Emily Wenger is a PhD student at the University of Chicago studying machine learning security and privacy. She’s particularly interested in understanding and preventing the unintended uses/abuses of facial recognition technology.
Emily and team has built Fawkes, a system that helps individuals inoculate their images against unauthorized facial recognition models. Fawkes achieves this by helping users add imperceptible pixel-level changes (we call them "cloaks") to their own photos before releasing them. When used to train facial recognition models, these "cloaked" images produce functional models that consistently cause normal images of the user to be misidentified.
* More about Fawkes http://sandlab.cs.uchicago.edu/fawkes/
* Full Research Paper - http://people.cs.uchicago.edu/~ravenben/publications/pdf/fawkes-usenix20.pdf
* Fawkes - http://sandlab.cs.uchicago.edu/fawkes/
* Source Code - https://github.com/Shawn-Shan/fawkes
mostra meno
Emily and team has built Fawkes, a system that helps individuals inoculate their images against unauthorized facial recognition models. Fawkes achieves this by helping users add imperceptible pixel-level changes (we call them "cloaks") to their own photos before releasing them. When used to train facial recognition models, these "cloaked" images produce functional models that consistently cause normal images of the user to be misidentified.
* More about Fawkes http://sandlab.cs.uchicago.edu/fawkes/
* Full Research Paper - http://people.cs.uchicago.edu/~ravenben/publications/pdf/fawkes-usenix20.pdf
* Fawkes - http://sandlab.cs.uchicago.edu/fawkes/
* Source Code - https://github.com/Shawn-Shan/fawkes
Informazioni
Autore | InfoSec Campus |
Sito | - |
Tag |
Copyright 2024 - Spreaker Inc. an iHeartMedia Company