Membership inference attacks against semantic segmentation models.
In: (AISec 2023 - Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 30 November 2023, Copenhagen, Denmark). 1601 Broadway, 10th Floor, New York, Ny, United States: Assoc Computing Machinery, 2023. 43-53 (AISec 2023 - Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security)
DOI
möglich sobald bei der ZB eingereicht worden ist.
Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we attempt to address an existing knowledge gap by conducting an exhaustive study of membership inference attacks and defences in the domain of semantic image segmentation. Our findings indicate that for certain threat models, these learning settings can be considerably more vulnerable than the previously considered classification settings. We quantitatively evaluate the attacks on a number of popular model architectures across a variety of semantic segmentation tasks, demonstrating that membership inference attacks in this domain can achieve a high success rate and defending against them may result in unfavourable privacy-utility trade-offs or increased computational costs.
Altmetric
Weitere Metriken?
Publikationstyp
Artikel: Konferenzbeitrag
Dokumenttyp
Typ der Hochschulschrift
Herausgeber
Korrespondenzautor
Schlagwörter
Membership Inference Attack ; Neural Networks ; Semantic Segmentation; Privacy
Keywords plus
ISSN (print) / ISBN
9798400702600
e-ISSN
ISBN
Bandtitel
Konferenztitel
AISec 2023 - Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security
Konferzenzdatum
30 November 2023
Konferenzort
Copenhagen, Denmark
Konferenzband
Quellenangaben
Band: ,
Heft: ,
Seiten: 43-53
Artikelnummer: ,
Supplement: ,
Reihe
Verlag
Assoc Computing Machinery
Verlagsort
1601 Broadway, 10th Floor, New York, Ny, United States
Hochschule
Hochschulort
Fakultät
Veröffentlichungsdatum
0000-00-00
Anmeldedatum
0000-00-00
Anmelder/Inhaber
weitere Inhaber
Anmeldeland
Priorität
Begutachtungsstatus
Förderungen
Technical University of Munich/Imperial College London Joint Academy for Doctoral Studies
Bavarian State Ministry for Science and the Arts
German Federal Ministry of Education and Research