Interpretable privacy with optimizable utility
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
Interpretable privacy with optimizable utility
Author(s) :
Ramon, Jan [Auteur]
Machine Learning in Information Networks [MAGNET]
Basu, Moitree [Auteur]
Machine Learning in Information Networks [MAGNET]

Machine Learning in Information Networks [MAGNET]
Basu, Moitree [Auteur]
Machine Learning in Information Networks [MAGNET]
Conference title :
ECML/PKDD 2020 - Workshop on eXplainable Knowledge Discovery in Data mining
City :
Ghent / Virtual
Country :
Belgique
Start date of the conference :
2020-09-14
English keyword(s) :
Privacy
Explainability
Constraint optimization
Explainability
Constraint optimization
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Théorie de l'information [cs.IT]
Mathématiques [math]/Statistiques [math.ST]
Statistiques [stat]/Machine Learning [stat.ML]
Informatique [cs]/Théorie de l'information [cs.IT]
Mathématiques [math]/Statistiques [math.ST]
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [en]
In this position paper, we discuss the problem of specifying privacy requirements for machine learning based systems, in an inter-pretable yet operational way. Explaining privacy-improving technology is a challenging ...
Show more >In this position paper, we discuss the problem of specifying privacy requirements for machine learning based systems, in an inter-pretable yet operational way. Explaining privacy-improving technology is a challenging problem, especially when the goal is to construct a system which at the same time is interpretable and has a high performance. In order to address this challenge, we propose to specify privacy requirements as constraints, leaving several options for the concrete implementation of the system open, followed by a constraint optimization approach to achieve an efficient implementation also, next to the interpretable privacy guarantees.Show less >
Show more >In this position paper, we discuss the problem of specifying privacy requirements for machine learning based systems, in an inter-pretable yet operational way. Explaining privacy-improving technology is a challenging problem, especially when the goal is to construct a system which at the same time is interpretable and has a high performance. In order to address this challenge, we propose to specify privacy requirements as constraints, leaving several options for the concrete implementation of the system open, followed by a constraint optimization approach to achieve an efficient implementation also, next to the interpretable privacy guarantees.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-02950994/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02950994/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02950994/document
- Open access
- Access the document
- document
- Open access
- Access the document
- ipcp.pdf
- Open access
- Access the document