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
- Jefferson County’s 16 ‘Boxcar Children’ an example of problems that may arise with new Census methodon August 27, 2021 at 4:31 pm
Sixteen children lived alone in a wooded stretch of New York’s Jefferson County last year, at least according to the 2020 census results released earlier this month.
- Redistricting to test new Census method for protecting user dataon August 27, 2021 at 3:00 pm
Sixteen children lived alone in a wooded stretch of New York's Jefferson County last year, at least according to the 2020 census results released earlier this month.
- TripleBlind’s Platform Analyzed by Polsinelli PCon August 26, 2021 at 10:07 am
TripleBlind ’s privacy claims relating to its Enterprise Data Privacy as a Service technology, which unlocks new revenue opportunities while automatically enforcing all privacy regulations, have been ...
- How will Facebook’s new privacy-enhancing technologies impact user data in digital advertising?on August 25, 2021 at 12:51 am
Facebook said that it is developing privacy-enhancing technologies which reduce its reliance on individual third-party data to deliver ads.
- Concerns around data privacy are rising, and blockchain is the solutionon August 22, 2021 at 7:18 am
Decentralized technologies are pushing the limit on safeguarding privacy, helping users to take back control and ownership of their data.
- Five worthy reads: Differential privacy—what it means for businesseson August 20, 2021 at 5:00 am
Five worthy reads is a regular column on five noteworthy items we’ve discovered while researching trending and timeless topics. In this edition, we explore one of the evolving privacy-enhancing ...
- States Are Suing the Census Bureau Over Its Attempts to Make Data More Privateon August 12, 2021 at 6:27 pm
Once a decade, the U.S. Census Bureau undertakes the massive challenge of counting every single person in the nation. We’re all asked to share sensitive information about ourselves—such as ...
- The census has a new process to protect your privacy. It also risks a less accurate counton August 10, 2021 at 12:41 pm
When the U.S. Census Bureau releases the first local results with demographic breakdowns from the 2020 decennial census on Thursday, the numbers will reflect a new method for protecting the ...
via Google News and Bing News