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-Based 2-D Frequency Estimation of Multiple Sinusoidalson May 2, 2021 at 9:22 pm
Frequency estimation of 2-D multicomponent sinusoidal signals is a fundamental issue in the statistical signal processing community that arises in various disciplines. In this article, we extend the ...
- Speech Vision: An End-to-End Deep Learning-based Dysarthric Automatic Speech Recognition Systemon May 2, 2021 at 8:20 pm
Dysarthria is a disorder that affects an individual’s speech intelligibility due to the paralysis of muscles and organs involved in the articulation process. As the condition is often associated with ...
- SUTD 50.039 Theory and Practice of Deep Learning Big Projecton May 2, 2021 at 9:55 am
Deep Learning approach to traffic speed prediction - EYLeong/traffic_prediction ...
- Dynamic Yield’s Deep Learning Product Recommendations Generate Exponential Revenue Returnson April 30, 2021 at 6:37 am
Customers implementing the self-training algorithm have witnessed double-digit uplifts in purchases and incremental revenue, compared to other personalized recommendation strategies New York, April 28 ...
- Deep learning model to predict fracture mechanisms of grapheneon April 30, 2021 at 6:29 am
Understanding fracture is critical to the design of resilient nanomaterials. Molecular dynamics offers a way to study fracture at an atomistic level, but is computationally expensive with limitations ...
- Deep-Learning Business Acquisition Makes Nano Dimension a Strong Buyon April 29, 2021 at 4:00 am
Some folks might not like Nano Dimensions’ aggressive pursuit of acquisitions. And, it is true that acquiring businesses is an expensive strategy. I’ll leave it to you to decide whether the company’s ...
- Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissectionon April 26, 2021 at 3:20 pm
Machine learning (ML) and deep learning (DL) can successfully predict high prevalence events in very large databases (big data), but the value of this methodology for risk prediction in smaller ...
- Deep Learning for Natural Language Processing - Lectures 2021on April 25, 2021 at 10:48 am
Deep Learning for Natural Language Processing - Lectures 2021 - dl4nlp-tuda2021/deep-learning-for-nlp-lectures ...
- Deep Instinct Raises $100M for its Cybersecurity Threat Prevention Platform Built on Deep Learningon April 22, 2021 at 6:07 am
Deep Instinct, cofounded by Guy Caspi, is an end-to-end cybersecurity detection platform that leverages deep learning to process threats faster than other solutions.
via Bing News