.png)
''' PRIVACY
''ARMOR'' PRIMERS '''
THE GENIUS OF THE FOUNDER FRAMERS is so well captured by the cartoon on Sam Daily Times : ''The Voice Of The Voiceless.'' It is to them that this very 'latest research' is dedicated.
IN RECENT YEARS COMPANIES HAVE been prowling the web for public photos associated with people's names that they can use to build -
Build enormous databases of faces and improve their facial recognition systems, adding to a growing sense that personal privacy is being lost, bit by digital bit.
A startup called Clearview A.I. for example, scrapped billions of online photos to build a tool for the police that could lead them from a face to Facebook account, revealing a person's identity.
NOW researchers are trying to foil those systems. A team of computer engineers at the University of Chicago has developed a tool that digitizes photos with pixel-level changes that confuse facial recognition systems.
Named Fawkes in honor of the Guy Fawkes mask favored by protesters worldwide, the software was made available to developers on the researchers' website last month. After being discovered by Hacker News, it has been downloaded more than 50,000 times.
The researchers are working on a free app version for noncoders, which they hope to make available soon.
The software is not intended to be just a tool for privacy loving individuals. If deployed across millions of images, it would be a broadside against face recognition systems, poisoning the accuracy of the so-called datasets they gather from the web.
''Our goal is to make Clearview go away,'' said Ben Zhao, a professor of computer science at the University of Chicago.
Fawkes converts an image - or ''cloaks'' it, in the researchers parlance - by subtly altering some of the features that facial recognition systems depend on when they construct a person's face print. In a research paper, reported earlier by OneZero, the team describes ''cloaking'' photos of the actress-
Actress Gwyneth Paltrow using the actor Patrick Dempsey's face, so that a system's learning what Ms. Paltrow looks like based on those photos would start associating her with some of the features on Mr. Dempsey's face.
The changes, usually subtle and not perceptible to the naked eye, would prevent the system from recognizing Ms. Paltrow when presented with a real, uncloaked photo of her.
In testing, the researchers were able to fool facial recognition systems from Amazon, Microsoft and the Chinese tech company Megvii.
IN RECENT YEARS COMPANIES HAVE been prowling the web for public photos associated with people's names that they can use to build -
Build enormous databases of faces and improve their facial recognition systems, adding to a growing sense that personal privacy is being lost, bit by digital bit.
A startup called Clearview A.I. for example, scrapped billions of online photos to build a tool for the police that could lead them from a face to Facebook account, revealing a person's identity.
NOW researchers are trying to foil those systems. A team of computer engineers at the University of Chicago has developed a tool that digitizes photos with pixel-level changes that confuse facial recognition systems.
Named Fawkes in honor of the Guy Fawkes mask favored by protesters worldwide, the software was made available to developers on the researchers' website last month. After being discovered by Hacker News, it has been downloaded more than 50,000 times.
The researchers are working on a free app version for noncoders, which they hope to make available soon.
The software is not intended to be just a tool for privacy loving individuals. If deployed across millions of images, it would be a broadside against face recognition systems, poisoning the accuracy of the so-called datasets they gather from the web.
''Our goal is to make Clearview go away,'' said Ben Zhao, a professor of computer science at the University of Chicago.
Fawkes converts an image - or ''cloaks'' it, in the researchers parlance - by subtly altering some of the features that facial recognition systems depend on when they construct a person's face print. In a research paper, reported earlier by OneZero, the team describes ''cloaking'' photos of the actress-
Actress Gwyneth Paltrow using the actor Patrick Dempsey's face, so that a system's learning what Ms. Paltrow looks like based on those photos would start associating her with some of the features on Mr. Dempsey's face.
The changes, usually subtle and not perceptible to the naked eye, would prevent the system from recognizing Ms. Paltrow when presented with a real, uncloaked photo of her.
In testing, the researchers were able to fool facial recognition systems from Amazon, Microsoft and the Chinese tech company Megvii.
To test the tool, I asked the team to cloak some images of my family and me. I then uploaded the originals and the cloaked images to Facebook, to see if they fooled the social network's facial recognition system.
It worked : Facebook tagged me in the original photo but did not recognize me in the cloaked version.
However, the changes to the photo were noticeable to the naked eye. In the altered images, I looked ghoulish, my 3-year-old daughter sprouted what looked like facial hair and my husband appeared to have a black eye.
The researchers had a few explanations for this. One is that the software is designed to match you with the face template of someone who looks as much unlike you as possible, pulling from a database of celebrity faces.
That usually ends up being a person of the opposite sex, which leads to obvious problems.
''Women get mustaches, and guys get extra eyelashes or eye shadow,'' Mr. Zhao said. He is enthusiastic about what he calls ''privacy armor'' and previously helped a bracelet that stops smart speakers from overhearing conversations.
The team says it plans to tweak the software so that it will no longer subtly change the sex of users.
The other issue is that my experiment wasn't what the tool was designed to do so Shawn Shan, a Ph.D. student at the University of Chicago was one of the creators of the Fawkes software, made the changes in my photos as extreme as possible to ensure that it worked.
Fawkes isn't intended to keep a facial recognition system like Facebook's from recognizing someone in a single photo. It's trying to more broadly corrupt facial recognition systems, performing an algorithm attack called data poisoning..
The Honor and Serving of the Latest Global Operational Research on Privacy and Technology, continues. The World Students Society thanks author, Kashmir Hill.
With respectful dedication to the Scientists, Designers, Students, Professors and Teachers of the world.
See Ya all prepare and register for Great Global Elections on The World Students Society : wssciw.blogspot.com and Twitter - !E-WOW! - The Ecosystem 2011:
''' Thwart - Thumb '''
It worked : Facebook tagged me in the original photo but did not recognize me in the cloaked version.
However, the changes to the photo were noticeable to the naked eye. In the altered images, I looked ghoulish, my 3-year-old daughter sprouted what looked like facial hair and my husband appeared to have a black eye.
The researchers had a few explanations for this. One is that the software is designed to match you with the face template of someone who looks as much unlike you as possible, pulling from a database of celebrity faces.
That usually ends up being a person of the opposite sex, which leads to obvious problems.
''Women get mustaches, and guys get extra eyelashes or eye shadow,'' Mr. Zhao said. He is enthusiastic about what he calls ''privacy armor'' and previously helped a bracelet that stops smart speakers from overhearing conversations.
The team says it plans to tweak the software so that it will no longer subtly change the sex of users.
The other issue is that my experiment wasn't what the tool was designed to do so Shawn Shan, a Ph.D. student at the University of Chicago was one of the creators of the Fawkes software, made the changes in my photos as extreme as possible to ensure that it worked.
Fawkes isn't intended to keep a facial recognition system like Facebook's from recognizing someone in a single photo. It's trying to more broadly corrupt facial recognition systems, performing an algorithm attack called data poisoning..
The Honor and Serving of the Latest Global Operational Research on Privacy and Technology, continues. The World Students Society thanks author, Kashmir Hill.
With respectful dedication to the Scientists, Designers, Students, Professors and Teachers of the world.
See Ya all prepare and register for Great Global Elections on The World Students Society : wssciw.blogspot.com and Twitter - !E-WOW! - The Ecosystem 2011:
''' Thwart - Thumb '''
Good Night and God Bless
SAM Daily Times - the Voice of the Voiceless
0 comments:
Post a Comment
Grace A Comment!