Each time you upload a photo or video to a social media platform, its facial recognition systems learn a little more about you. These algorithms ingest data about who you are, your location and people you know — and they’re constantly improving.
As concerns over privacy and data security on social networks grow, U of T Engineering researchers led by Professor Parham Aarabi (ECE) and graduate student Avishek Bose (ECE MASc candidate) have created an algorithm to dynamically disrupt facial recognition systems.
“Personal privacy is a real issue as facial recognition becomes better and better,” says Aarabi. “This is one way in which beneficial anti-facial-recognition systems can combat that ability.”
Their solution leverages a deep learning technique called adversarial training, which pits two artificial intelligence algorithms against each other. Aarabi and Bose designed a set of two neural networks: the first working to identify faces, and the second working to disrupt the facial recognition task of the first. The two are constantly battling and learning from each other, setting up an ongoing AI arms race.
The result is an Instagram-like filter that can be applied to photos to protect privacy. Their algorithm alters very specific pixels in the image, making changes that are almost imperceptible to the human eye.
“The disruptive AI can ‘attack’ what the neural net for the face detection is looking for,” says Bose. “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.”
Aarabi and Bose tested their system on the 300-W face dataset, an industry standard pool of more than 600 faces that includes a wide range of ethnicities, lighting conditions and environments. They showed that their system could reduce the proportion of faces that were originally detectable from nearly 100 per cent down to 0.5 per cent.
“The key here was to train the two neural networks against each other — with one creating an increasingly robust facial detection system, and the other creating an ever stronger tool to disable facial detection,” says Bose, the lead author on the project. The team’s study will be published and presented at the 2018 IEEE International Workshop on Multimedia Signal Processing later this summer.
In addition to disabling facial recognition, the new technology also disrupts image-based search, feature identification, emotion and ethnicity estimation, and all other face-based attributes that could be extracted automatically.
Next, the team hopes to make the privacy filter publicly available, either via an app or a website.
“Ten years ago these algorithms would have to be human defined, but now neural nets learn by themselves — you don’t need to supply them anything except training data,” says Aarabi. “In the end they can do some really amazing things. It’s a fascinating time in the field, there’s enormous potential.”
The Latest on: Deep learning
via Google News
The Latest on: Deep learning
- Art? Music? The five senses? How deep learning is making AI more human on September 18, 2018 at 9:18 am
How do you ethically programme an autonomous car? What is the best way to train a robot surgeon? Can machines be taught to exhibit aesthetic sensibilities? These are just some of the questions that th... […]
- DarwinAI Emerges from Stealth with Powerful Design, Optimization and Explainability Platform for Deep Learning on September 18, 2018 at 8:11 am
WATERLOO, Ontario, Sept. 18, 2018 (GLOBE NEWSWIRE) -- DarwinAI, a Waterloo, Canada startup creating next generation technologies for Artificial Intelligence development, announced today it is ... […]
- MathWorks Expands Deep Learning Capabilities in Release 2018b of the MATLAB and Simulink Product Families on September 18, 2018 at 6:00 am
NATICK, Mass.--(BUSINESS WIRE)--MathWorks today introduced Release 2018b of MATLAB and Simulink. The release contains significant enhancements for deep learning, along with new capabilities and bug fi... […]
- Deep learning courses for nlp market insights shared in detailed report on September 18, 2018 at 4:48 am
Deep learning is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Research analysis on the global deep learning cour... […]
- IoT Edge Processing With Apache NiFi, MiniFi, and Multiple Deep Learning Libraries: Part 2 on September 17, 2018 at 9:59 am
We had a lot of fun at the conference, with the looks of interesting things going on. There's an interesting new way to easily run TensorFlow on YARN! It's called Submarine, and I'll do an article ... […]
- Exploring Deep Learning Models for Compression and Acceleration on September 17, 2018 at 9:04 am
EdgeVerve’s Business Applications built on AI platform Infosys Nia™ enables your enterprise to manage specific business areas and make the move from a deterministic to cognitive approach. […]
- Microsoft (MSFT) Adds Deep Learning AI Tools with Lobe Buyout on September 17, 2018 at 7:13 am
Microsoft (MSFT - Free Report) recently acquired Lobe, a startup based in San Francisco, CA. However, the terms of the deal have been kept under wraps. Notably, this buyout adds to Microsoft’s growing ... […]
- Review: Keras sails through deep learning on September 17, 2018 at 3:06 am
Keras proper, a high-level front end for building neural network models, ships with support for three back-end deep learning frameworks: TensorFlow, CNTK, and Theano. Amazon is currently working on de... […]
- Microsoft acquires deep learning startup Lobe on September 13, 2018 at 7:38 pm
Microsoft Corp. said Thursday its acquired a small San Francisco-based startup called Lobe Artificial Intelligence Inc. as part of its continuing push to help people create deep learning models ... […]
via Bing News