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
[google_news title=”” keyword=”differential privacy” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
- The Impact of Personalized Ads: Navigating AI and Regulatory Realitieson March 28, 2024 at 12:39 am
In recent times, the digital advertising sphere has faced several hassles with the impending deprecation of third-party ...
- A change in the machine learning landscapeon March 19, 2024 at 2:00 am
The RoPPFL framework introduces a blend of local differential privacy (LDP) and similarity-based Robust Weighted Aggregation (RoWA) techniques. LDP protects data privacy by adding calibrated noise ...
- Are Law Enforcement Crackdowns Fueling a Ransomware Gang War?on March 17, 2024 at 6:25 am
As law enforcement disrupts ransomware gangs, experts explain ‘power abhors a vacuum’ and talk about the rise of the “Five Families”.
- The women in AI making a differenceon March 10, 2024 at 10:45 am
Harvard professor Cynthia Dwork made waves decades ago in the fields of AI fairness, differential privacy and distributed computing. And Cynthia Breazeal, a roboticist and professor at MIT and the ...
- An integrated shuffler optimizes the privacy of personal genomic data used for machine learningon February 15, 2024 at 9:28 am
A method called differential privacy can be used to break up the data in a way that guarantees privacy, but this results in a "noisy" model that limits its utility for precise gene-based research.
- Shuffling the deck for privacyon February 15, 2024 at 8:37 am
A method called differential privacy can be used to break up the data in a way that guarantees privacy, but this results in a “noisy” model that limits its utility for precise gene-based research.
- How To Navigate The Privacy Crossroads Between AI And HIPAAon December 21, 2023 at 9:27 pm
Organizations should adopt methods such as safe harbor, which is based on removing specific identifiers from the data set and differential privacy, as one possible solution for de-identification.
- COMP_SCI 396: Differential Privacy: from Foundations to Machine Learningon April 21, 2023 at 8:41 am
The course will be a proof-based theoretical course and assume sufficient mathematical maturity, in particular in probability and linear algebra. Important concepts will be reviewed. A good ...
- Differential Equations: Linear Algebra and NxN Systems of Differential Equationson January 7, 2023 at 11:59 pm
However, 2U has committed to preserving robust privacy of individual data for all learners who use the platform. For more information see the edX Help Center. Differential equations are the ...
- Apple and Privacyon May 17, 2021 at 12:35 pm
Apple proposes that indirect advertising using differential privacy and other tools enable just-as-good results. That the incredible amounts of data being collected for targeted ads are not only ...
via Google News and Bing News