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
- Deep learning algorithm cuts spine MRI exam time by about 50 percent, study findson December 3, 2021 at 7:30 pm
USA: The use of a deep learning algorithm for reconstructing spine MRI exams gives images comparable to those taken with a conventional MRI, reveals a recent study. Also, deep learning reduces spine ...
- Top 12 AI and machine learning announcements at AWS re:Invent 2021on December 3, 2021 at 6:30 pm
Invent 2021 conference, Amazon announced a slew of new Amazon Web Services features powered by AI and machine learning.
- Univ. of Washington deep learning researchers ‘hallucinate’ protein designs from scratchon December 2, 2021 at 7:52 am
New protein structures not seen in nature have emerged from deep learning software deployed by University of Washington researchers and their colleagues. The approach is a step toward building ...
- Deep Trouble for Deep Learning: Hidden Technical Debton December 2, 2021 at 2:27 am
In order to take advantage of the full potential of deep learning, enterprises will need platforms that can help resolve significant challenges with technical debt.
- Deep Learning Dreams Up New Protein Structureson December 1, 2021 at 7:56 am
Just as convincing images of cats can be created using artificial intelligence, new proteins can now be made using similar tools.
- Physics-informed deep learning to assess carbon dioxide storage siteson December 1, 2021 at 6:52 am
Pumping carbon dioxide underground may help combat the warming of the atmosphere but finding appropriate underground sites that could safely serve as reservoirs can be complicated.
- Deep Learning Market Technological Advancements, Evolving Industry Trends and Insightson November 30, 2021 at 5:23 am
Deep learning algorithms are being increasingly used in contact centers as the adoption of these algorithms help them in improving the first call resolution process reducing call durations curtailing ...
- The good, the bad and the ugly of deep learning technologyon November 30, 2021 at 1:30 am
The use of deep learning for social media and online content generation has gained equal parts attraction and concern in recent years. With a reputation as a cog in the fake news machine, deep ...
- A deep learning method to automatically enhance dog animationson November 26, 2021 at 9:30 am
Researchers at Trinity College Dublin and University of Bath have recently developed a model based on deep neural networks that could help to improve the quality of animations containing quadruped ...
via Bing News