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 Framework SINGA Graduates to Top-Level Apache Projecton November 19, 2019 at 6:03 am
It is essential to scale deep learning via distributed computing as...deep learning models are typically large and trained over big datasets, which may take hundreds of days using a single GPU. There ...
- The Cerebras CS-1 computes deep learning AI problems by being bigger, bigger, and bigger than any other chipon November 19, 2019 at 5:06 am
Deep learning is all the rage these days in enterprise circles, and it isn’t hard to understand why. Whether it is optimizing ad spend, finding new drugs to cure cancer, or just offering better, more ...
- Neural architecture search automates the development of deep learning-based models for cancer researchon November 18, 2019 at 12:58 pm
Argonne researchers have created a neural architecture search that automates the development of deep-learning-based predictive models for cancer data. While increasing swaths of collected data and ...
- Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctionson November 15, 2019 at 2:22 am
Here we present a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived.
- Deep learning segmentation of major vessels in X-ray coronary angiographyon November 15, 2019 at 2:22 am
In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels ...
- Deep Learning Market 2019 Drivers, Opportunities, Trends, and Forecast by 2025 – MRE Research Reporton November 14, 2019 at 11:01 pm
Nov 15, 2019 (Heraldkeepers) -- New York, November 15, 2019: The Deep Learning Market is segmented on the Basis of End-User Type, Application Type, Solution Type and Regional Analysis. By End-User ...
- Going deeper: Moveworks snags $75M in new money to bolster deep learning in enterpriseon November 14, 2019 at 4:30 pm
Unlike some applications of BERT or Transformer, which "fine tune" the system, a relatively simpler task, Moveworks is "pre-training" the BERT model, which means developing the initial corpus of text ...
- Amazon Saw 15-Fold Jump In Forecast Accuracy With Deep Learning And Other AI Statson November 14, 2019 at 6:04 am
When Amazon switched from traditional machine learning techniques to deep learning in 2015, it saw a 15-fold increase in the accuracy of its forecasts, a leap that has enabled it to roll-out its ...
- Deep Learning Market by Top Players -Advanced Micro Devices, ARM Ltd, Clarifai, Entilic, Google, & Moreon November 13, 2019 at 9:59 pm
Nov 14, 2019 (Hitech News Daily via COMTEX) -- The World Deep Learning Market is bound to growth by 2025, as per the latest report by Big Market Research (BMR). Deep learning is a part of machine ...
via Bing News