Skip to main content

Researchers Design a Filter to Defeat Facial Recognition Software

Most social networks these days, including Facebook, use facial recognition on your photos whenever you make an upload to gather data on you. In addition to social networks, the web is also full of similar software that is able to automatically recognize a person and figure out other things such as ethnicity, gender, and the environment.
As privacy concerns have grown recently, University of Toronto researchers have developed an AI that counters facial recognition software in a subtle way, by making minute adjustments to your photos. The research, led by professor Parham Aarabi and Avishek Bose (an MASc candidate), has successfully disrupted common facial recognition systems.
Personal privacy is a real issue as facial recognition becomes better and better. This is one way in which beneficial anti-facial-recognition systems can combat that ability.

ALSO, READ

AI vs AI

In order to strengthen their solution, the team used an AI technique known as adversarial training in which two opposing neural networks consistently learn from each other. So in their case, they developed two AIs: one that recognizes faces, and a second one that disrupts it by constantly training itself to counter the first one.
This way, both AI’s keep learning from each other and keep expanding on ways to prevent facial recognition. Avishek Bose says,

ALSO, READ

The disruptive AI can ‘attack’ what the neural net for the face detection is looking for. If the detection AI is looking for the corner of the eyes, for example, it adjusts the corner of the eyes so they’re less noticeable. It creates very subtle disturbances in the photo, but to the detector they’re significant enough to fool the system.
We can expect it work like a filter or a third-party plug-in that slightly modifies your image for you before you upload it to a social network. The researchers tested it out using a library of 600 different faces that were originally detectable, the new solution managed to reduce facial detection accuracy from 100 to 0.5 percent.
Via UoT

Comments

Popular posts from this blog

Develop your own game by learning these free courses

We recently recommended courses you should learn before you will launch your first startup in order to avoid some common mistakes. In Quick Tips today, we’ll recommend you some free courses that will help you make your first game and begin your career as a developer. Before we highlight the details of the courses you ought to take, here are some introductory courses which will prepare you to learn these courses more effectively; Java Programming Basics  – Prepare yourself for programming on Android and the Web Introduction to JavaScript  – Create animations and understand variables and strings. When you have gone through those courses above then proceed to ones given below to develop your first game: 1. Create a 2048 game in just 1 day For those who have zero experience in programming and don’t want to take the above courses, then enroll in this course from Udacity. You will learn the basics of HTML and CSS as well as their interaction with JavaScript. ...

The upgraded Google News app is now available on iOS and Android

One of the more intriguing announcements at Google IO 2018 was of  a new Google News app  to take the place of the Google Play NewsStand, which was initially launched in 2013.  After describing the new Google News app  in a dedicated page for the app on its website, Google has now officially released the app on the  App Store  and  Google Play . Google Play NewsStand was used as a resource to get news around the world. The news would be of every category, even the news which doesn’t interest the user. Whereas with this new Google news app, the artificial intelligence of Google shows you the news you want to see, which you usually search for on Google. According to Google , the Google News app now  “uses a new set of AI techniques to take a constant flow of information as it hits the web, analyze it in real time and organize it into storylines.”  Artificial intelligence(AI) gives the app an ability to process and sort the news from...

Huawei Mate 10 Pro: A Premium Flagship With Some Odd Omissions

When Huawei had launched, they were known as a brand that mostly dealt with budget smartphones and even their flagships were not up to the standards that people expected at that time. However, times have now changed and leading the innovation front nowadays is Huawei. A few of their flagships in the recent year or so have been nothing short of impressive but this year’s Mate 10 line up has changed the brand image forever and consumers now know that Huawei is a serious market player and should not be taken lightly. We’ve already reviewed the  Mate 10 Lite and there was a lot to like about that phone. Today we have with us the most expensive one of the bunch, the Mate 10 Pro. For a more in-depth review and understanding of various Mate 10 Pro features, do watch the video review linked below. Design Like most of the flagships in the industry, Huawei also makes use of some premium material on the Mate 10 Pro. You have curved Gorilla Glass on the front and back and where th...