Interpretable privacy with optimizable utility

Jan Ramon (1) , Moitree Basu (1)

1 MAGNET - Machine Learning in Information Networks

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.

Mots clés: Privacy; Explainability; Constraint optimization

Domaines: Intelligence artificielle [cs.AI]; Théorie de l'information [cs.IT]; Statistiques [math.ST]; Machine Learning [stat.ML]

Jan Ramon, Moitree Basu. Interpretable privacy with optimizable utility. ECML PKDD 2020 - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases, Sep 2020, Ghent / Virtual, Belgium. ⟨hal-02950994⟩