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 transfer learning has now been used to classify galaxies with expert-level accuracyon January 31, 2020 at 11:56 pm
Last year in September, researchers used deep learning to probe into dark matter in an industry first. Now, the same technique has been used to study galaxies. In the paper titled "Deep Learning at ...
- 5 Soon-to-Be Trends in Artificial Intelligence And Deep Learningon January 31, 2020 at 5:10 pm
AI’s major headwind is the cost of the investment, which will skew returns in the short-term. When the turnaround occurs, however, companies who are making the investment can expect to be rewarded ...
- Deep Learning Models for Histopathological Classification of Gastric and Colonic Epithelial Tumourson January 30, 2020 at 2:40 am
In 2018, there were 1,033,701 new cases and 782,685 deaths due to stomach cancer, and 1,096,601 new cases and 551,269 deaths due to colon cancer. Here, we propose deep learning models to classify ...
- Deep Learning Chipset Market Size, Share 2020 Supply, Consumption, Cost and Profit analysis and forecast to 2024| Says Market Reports Worldon January 29, 2020 at 9:37 pm
Deep Learning Chipset Market 2020 :- The Deep Learning Chipset Market has been created based on an in-depth market analysis with inputs from industry experts. The report covers the growth prospects ...
- Concentric launches with a deep learning approach to fixing broken file permissionson January 29, 2020 at 2:08 pm
Concentric Inc. launched today with $7.5 million in a Series A funding and an approach to document-level security that relies upon the artificial intelligence technique of deep learning to identify ...
- Opening the AI box: can deep learning predict cancer recurrence?on January 29, 2020 at 2:13 am
The deep-learning algorithm automatically annotates a 3D whole-mount pathology image and presents the discovered features in an understandable way. The patches with high probability of cancer ...
- Lab Materials for MIT 6.S191: Introduction to Deep Learningon January 29, 2020 at 12:31 am
This repository contains all of the code and software labs for MIT 6.S191: Introduction to Deep Learning! All lecture slides and videos are available on the course website. The 2020 6.S191 labs will ...
- Reality Engines offers a deep learning tour de force to challenge Amazon et al in Enterprise AIon January 28, 2020 at 9:28 am
Most exciting of all is that the tiny 18-person team has some very novel takes on deep learning forms of AI, the product of seasoned vets in machine learning technology and products. This is no me-too ...
- Near Real-Time Wildfire Progression Monitoring with Sentinel-1 SAR Time Series and Deep Learningon January 28, 2020 at 2:11 am
In this communication, we investigated and demonstrated the potential of Sentinel-1 SAR time series with a deep learning framework for near real-time wildfire progression monitoring. The deep learning ...
via Bing News