New machine learning method developed by researchers at the University of Helsinki, Aalto University and Waseda University of Tokyo can use for example data on cell phones while guaranteeing data subject privacy.
Modern AI is based on machine learning which creates models by learning from data. Data used in many applications such as health and human behaviour is private and needs protection. New privacy-aware machine learning methods have been developed recently based on the concept of differential privacy. They guarantee that the published model or result can reveal only limited information on each data subject.
Privacy-aware machine learning
“Previously you needed one party with unrestricted access to all the data. Our new method enables learning accurate models for example using data on user devices without the need to reveal private information to any outsider”, Assistant Professor Antti Honkela of the University of Helsinki says.
The group of researchers at the University of Helsinki and Aalto University, Finland, has applied privacy-aware methods for example to predicting cancer drug efficacy using gene expression.
“We have developed these methods with funding from the Academy of Finland for a few years, and now things are starting to look promising. Learning from big data is easier, but now we can also get results from smaller data”, Academy Professor Samuel Kaski of Aalto University says.
Learn more: New AI method keeps data private
The Latest on: Differential privacy
What is differential privacy and how can it protect your data?
on March 19, 2018 at 5:37 am
Tech companies can use differential privacy to collect and share aggregate data about user habits, while maintaining individual privacy. Credit: Tim Snell/Flickr, CC BY-ND It's no secret that big tech companies like Facebook, Google, Apple and Amazon are ... […]
Explainer: what is differential privacy and how can it protect your data?
on March 18, 2018 at 11:55 pm
Victoria State Government provides funding as a strategic partner of The Conversation AU. Deakin University provides funding as a member of The Conversation AU. It’s no secret that big tech companies like Facebook, Google, Apple and Amazon are ... […]
What is differential privacy and how can it protect consumer data?
on March 18, 2018 at 2:33 pm
It’s no secret that big tech companies like Facebook, Google, Apple and Amazon are increasingly infiltrating our personal and social interactions to collect vast amounts of data on us every day. At the same time, privacy violations in cyberspace ... […]
Apple Details Its Learning System Architecture Which Uses Differential Privacy to Improve User Features
on December 6, 2017 at 12:49 pm
Apple has posted a new entry on its Machine Learning blog detailing the company's learning system architecture which uses differential privacy to enhance user features. Differential privacy aims obtain accurate queries from statistical databases while ... […]
Apple locked in differential privacy debate
on October 31, 2017 at 9:31 am
A new data collection technique being used by firms including Apple could let companies collect app use information while protecting your identity. Differential privacy adds "noise" to data harvested from your device, preventing it from being traced back. […]
Apple now collects data from Safari using differential privacy to identify problem websites
on September 26, 2017 at 3:30 am
With the launch of macOS High Sierra, Apple is making some changes to Safari. One of the key changes is the introduction of differential privacy technology which gathers data about the websites users visit in order to identify those that are problematic ... […]
Apple starts collecting browsing data in Safari using its differential privacy tech
on September 25, 2017 at 10:27 am
Today’s public release of macOS High Sierra brings with it some key updates to Safari — including the ability to disable cross-site cookie tracking and turn off autoplaying ads. Arriving alongside those features is a less publicized new addition to ... […]
Apple's 'differential privacy' still collects too much specific data, study says
on September 15, 2017 at 7:49 pm
Apple's use of "differential privacy" — a method that inserts random noise into data as it's collected en masse — doesn't go far enough to protect personal information, a study suggested this week. Another concern is that Apple keeps its loss parameter ... […]
As Apple starts analyzing web browsing & health data, how comfortable are you with differential privacy?
on July 7, 2017 at 7:00 am
An Apple software engineer recently revealed that Apple is now rolling out its use of differential privacy to cover both web browsing and health data, as it now uses the technique to process millions of pieces of daily information from device users. […]
via Google News and Bing News