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.”
Receive an email update when we add a new DEEP LEARNING article.
The Latest on: Deep learning
via Google News
The Latest on: Deep learning
- insideBIGDATA Guide to Data Platforms for Artificial Intelligence and Deep Learning on November 13, 2018 at 10:37 am
With AI and DL, storage is cornerstone to handling the deluge of data constantly generated in today’s hyperconnected world. It is a vehicle that captures and shares data to create business value. In t... […]
- Deep Learning Chipset Market Will Reach Revenue of US$1,264.78 Mn by the End of 2025 on November 13, 2018 at 12:54 am
Global Deep Learning Chipset market report provides analysis for the period 2015 – 2025, wherein the period from 2017 to 2025 is the forecast and 2016 is the base year. The data for 2015 has been incl... […]
- BOXX Demos New Deep Learning Workstation and More at SC18 on November 12, 2018 at 10:32 am
News and research before you hear about it on CNBC and others. Claim your 2-week free trial to StreetInsider Premium here. AUSTIN, TEXAS, Nov. 12, 2018 (GLOBE NEWSWIRE) -- BOXX Technologies, the leadi... […]
- Top 10 Machine Learning, Deep Learning, and Data Science Courses for Beginners (Python and R) on November 12, 2018 at 10:32 am
Did you know that 50- 80% of your enterprise business processes can be automated with AssistEdge? Identify processes, deploy bots and scale effortlessly with AssistEdge. Data Science, Machine ... […]
- How NLP, ML and Deep Learning Can Transform Your CX Strategy on November 11, 2018 at 5:26 am
The post aims to give the reader a gentle overview of NLP, ML and Deep Learning and make the connection of how it can be applied in the context of customer experience and support. Machine learning Ima... […]
- Bayesian Deep Learning for Exoplanet Atmospheric Retrieval on November 8, 2018 at 7:33 pm
Over the past decade, the study of exoplanets has shifted from their detection to the characterization of their atmospheres. Atmospheric retrieval, the inverse modeling technique used to determine an ... […]
- How Deep Learning can solve the problem of global climate change on November 7, 2018 at 7:51 am
With the help of a use case, Dr Patrick Vetter, Head of Competence Center Data Science at Supper and Supper GMBH explains how a deep learning methodology can locate and segment wind turbines on satell... […]
- Deep Learning for Medical Imaging Fares Poorly on External Data on November 7, 2018 at 7:07 am
November 07, 2018 - A deep learning model trained to identify pneumonia on a contained sample of medical images was unable to achieve the same level of accuracy when let loose on data from external he... […]
- Deep Learning AI diagnosed Alzheimer’s 6-years earlier than conventional methods on November 7, 2018 at 4:29 am
One of the most important things for combating Alzheimer’s disease is early diagnosis so treatments for the condition can start before damage is severe. The earlier interventions start, the better the ... […]
via Bing News