Dissecting Membership Inference Risk in Machine Learning

• Membership inference attacks (MIA) have been identified as a distinct threat to privacy when sensitive personal data are used to train the machine learning (ML) models. This work is aimed at deepening our understanding with respect to the existing black-box MIAs while introducing a new label only MIA model. The proposed MIA model can successfully exploit the well generalized models challenging the conventional wisdom that states generalized models are immune to membership inference. Through systematic experimentation, we show that the proposed MIA model can outperform the existing attack models while being more resilient towards manipulations to the membership inference results caused by the selection of membership validation data. 

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

Data privacy

Membership inference attack

Privacy preserving machine learning

Privacy-preserving techniques

Attack modeling

Black boxes

Generalized models

Inference attacks

Inference risk

Machine learning models

Machine-learning

Privacy preserving

Machine learning

Skövde Artificial Intelligence Lab (SAIL)

Skövde Artificial Intelligence Lab (SAIL)

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)