Sökning: id:"swepub:oai:DiVA.org:his-20889" >
Dissecting Membersh...
Dissecting Membership Inference Risk in Machine Learning
-
- Senavirathne, Navoda (författare)
- Högskolan i Skövde,Institutionen för informationsteknologi,Forskningsmiljön Informationsteknologi,Skövde Artificial Intelligence Lab (SAIL),School of Informatics, University of Skövde, Skövde, Sweden
-
- Torra, Vicenç (författare)
- Umeå universitet,Institutionen för datavetenskap,Department of Computer Science, University of Umeå, Sweden,Skövde Artificial Intelligence Lab (SAIL)
-
(creator_code:org_t)
- 2022-01-11
- 2022
- Engelska.
-
Ingår i: Cyberspace Safety and Security. - Cham : Springer. - 9783030940287 - 9783030940294 ; , s. 36-54
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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)
Hitta via bibliotek
Till lärosätets databas