Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Windsor

$23,000.00

Privacy-Preserving Machine Learning Techniques

EF 2019-20

Résumé
The advancement of Artificial Intelligence (AI) is transforming our society from ordinary applications like Alexa and Hey Google to extraordinary innovations to predict behavior, diagnose disease, and optimize operations. Countries that lead in AI research and application are expected to see a doubling of their economic growth rates. Canada already produces some of the most sought-after AI talent in the world and has committed upwards of $1 billion in investment as interest grows among academic institutions, private companies, and governments. Machine Learning (ML) drives AI development forward with the speed it currently has because of two important breakthroughs: (1) the realization which means teaching computers to learn themselves and (2) the huge increase of the amount of the available information for analysis. Along with opportunity, ML techniques come with many privacy risks. In order to keep Canada a leader in this field, we need to prepare not only a new generation skilled in ML, but also scalable platforms to enable privacy-preserving ML techniques. We need to enable innovation while protecting privacy. In particular, this proposal will address privacy challenges arising when using ML techniques to analyze user-generated sensitive data by: i) developing practical privacy-preserving ML mechanisms to prevent disclosures of sensitive data in the context of cloud environment; ii) developing practical collaborative privacy-preserving ML mechanisms when multiple data owners compute a ML task on their aggregated data; and iii) developing robust privacy-preserving ML prediction to prevent information leakage through the prediction outputs. This proposed research will extend the current body of knowledge on the privacy aspects of ML technologies. It will have important applications to assess the usability of privacy-preserving ML techniques, design supporting platforms, and enhance curricula. The expertise gained will directly involve 4 graduate students and indirectly affect a huge number of researchers and practitioners where the privacy aspects hinder them from benefiting from ML. As a member of the Canadian Institute for Cybersecurity (CIC), I will discuss and validate the results with selected industry partners including Siemens, TD bank, Bell, and IBM, which are corporate members (research and development partners) working with CIC at the University of New Brunswick (UNB). CIC corporate members discuss the importance of the aforementioned challenges in smart grid and health domains and are interested in finding practical solutions. I will create a lab for privacy-preserving ML and together with my HQP we will transfer the results of this research to government, industry, and researchers. Finally, I will publish research results in top-tier research venues and make them available on open-access repositories. This will guide future researchers and have the potential to ensure a prosperous future for government and industry.*****
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2019-05689
Name nom
Alhadidi, Dima
Department département
Office of Research Services (ORS)
Organization id
37
Institution établissement
University of Windsor
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2019
Competition year année de concours
2019
Award amount
23000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2700
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information technology
Research subject fr
Technologie de l'information
Installment
inst:1 - 5
Partie
1
Nb partie
5
Application title
Privacy-Preserving Machine Learning Techniques
Keyword
NSERC
Application summary
The advancement of Artificial Intelligence (AI) is transforming our society from ordinary applications like Alexa and Hey Google to extraordinary innovations to predict behavior, diagnose disease, and optimize operations. Countries that lead in AI research and application are expected to see a doubling of their economic growth rates. Canada already produces some of the most sought-after AI talent in the world and has committed upwards of $1 billion in investment as interest grows among academic institutions, private companies, and governments. Machine Learning (ML) drives AI development forward with the speed it currently has because of two important breakthroughs: (1) the realization which means teaching computers to learn themselves and (2) the huge increase of the amount of the available information for analysis. Along with opportunity, ML techniques come with many privacy risks. In order to keep Canada a leader in this field, we need to prepare not only a new generation skilled in ML, but also scalable platforms to enable privacy-preserving ML techniques. We need to enable innovation while protecting privacy. In particular, this proposal will address privacy challenges arising when using ML techniques to analyze user-generated sensitive data by: i) developing practical privacy-preserving ML mechanisms to prevent disclosures of sensitive data in the context of cloud environment; ii) developing practical collaborative privacy-preserving ML mechanisms when multiple data owners compute a ML task on their aggregated data; and iii) developing robust privacy-preserving ML prediction to prevent information leakage through the prediction outputs. This proposed research will extend the current body of knowledge on the privacy aspects of ML technologies. It will have important applications to assess the usability of privacy-preserving ML techniques, design supporting platforms, and enhance curricula. The expertise gained will directly involve 4 graduate students and indirectly affect a huge number of researchers and practitioners where the privacy aspects hinder them from benefiting from ML. As a member of the Canadian Institute for Cybersecurity (CIC), I will discuss and validate the results with selected industry partners including Siemens, TD bank, Bell, and IBM, which are corporate members (research and development partners) working with CIC at the University of New Brunswick (UNB). CIC corporate members discuss the importance of the aforementioned challenges in smart grid and health domains and are interested in finding practical solutions. I will create a lab for privacy-preserving ML and together with my HQP we will transfer the results of this research to government, industry, and researchers. Finally, I will publish research results in top-tier research venues and make them available on open-access repositories. This will guide future researchers and have the potential to ensure a prosperous future for government and industry.*****