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”]- Digital’s dirty little secret: How to clean up the privacy washing mess?on May 1, 2024 at 10:01 pm
Addressing concerns related to privacy washing requires a multi-faceted approach involving collaboration among regulators, industry stakeholders, consumers & technology experts, say industry players ...
- 10 Steps to Take After Clicking on a Phishing Link in 2024on May 1, 2024 at 5:46 am
Learn how to protect yourself from phishing scams and explore 10 essential steps to take after clicking on a phishing link.
- FEDML Empowers On-Premise AI Innovation at DENSOon April 30, 2024 at 11:25 am
Press Release FEDML, the company providing "Your Generative AI Platform at Scale," today announced its partnership with DENSO, one of the largest automotive suppliers in the world, to empower fully on ...
- Google Privacy Sandbox and What Brands Need to Knowon April 23, 2024 at 5:49 am
How Google Privacy Sandbox is a privacy-first alternative, and how it fits into the future of cookieless marketing and advertising.
- Are Data Privacy And Generative AI Mutually Exclusive?on April 22, 2024 at 5:44 am
DP offers benefits such as enhanced privacy, regulatory compliance and customer trust, enabling companies to innovate and compete while protecting sensitive data. Its quantifiable privacy guarantees ...
- PVML combines an AI-centric data access and analysis platform with differential privacyon April 15, 2024 at 11:17 am
PVML is offering an interesting solution by combining a ChatGPT-like tool for analyzing data with the safety guarantees of differential privacy. Using retrieval-augmented generation (RAG), PVML ca ...
- PVML combines an AI-centric data access and analysis platform with differential privacyon April 15, 2024 at 11:17 am
PVML is offering an interesting solution by combining a ChatGPT-like tool for analyzing data with the safety guarantees of differential privacy. The company was founded by husband-and-wife team ...
- 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 ...
- Apple Shares Differential Privacy Insights for Emoji and QuickType Keyboardon December 6, 2017 at 9:37 am
In the most recent issue of Apple’s Machine Learning Journal, titled “Learning with Privacy at Scale,” the team working on differential privacy shares details ...
via Google News and Bing News