PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Bani-Harouni, D.* ; Mueller, T.T.* ; Rueckert, D.* ; Kaissis, G.

Gradient Self-alignment in Private Deep Learning.

In: (26th International Conference on Medical Image Computing and Computer-Assisted Intervention , MICCAI 2023, 8 - 12 October 2023, Vancouver, CANADA). Berlin [u.a.]: Springer, 2023. 89-97 (Lect. Notes Comput. Sc. ; 14393)
DOI
Open Access Green möglich sobald Postprint bei der ZB eingereicht worden ist.
Differential Privacy (DP) has become a gold-standard to preserve privacy in deep learning. Intuitively speaking, DP ensures that the output of a model is approximately invariant to the inclusion or exclusion of a single individual’s data from the training set. There is, however, a trade-off between privacy and utility. DP models tend to perform worse than non-DP models trained on the same data. This is caused by the clipping of per-sample gradients and the addition of noise required for DP guarantees causing an obfuscation of the individual data point’s contribution. In this work, we propose a method to reduce this discrepancy by improving the alignment between the per-sample gradients of each individual training sample with its non-DP gradient by increasing their cosine similarity. Optimizing the alignment in only a relevant subset of gradient dimensions, further improves the performance. We evaluate our method on CIFAR-10 and a pediatric pneumonia chest x-ray dataset.
Altmetric
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Differential Privacy ; Gradient Alignment ; Private Learning
Sprache englisch
Veröffentlichungsjahr 2023
HGF-Berichtsjahr 2023
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel 26th International Conference on Medical Image Computing and Computer-Assisted Intervention , MICCAI 2023
Konferzenzdatum 8 - 12 October 2023
Konferenzort Vancouver, CANADA
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 14393, Heft: , Seiten: 89-97 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)
POF Topic(s) 30205 - Bioengineering and Digital Health
Forschungsfeld(er) Enabling and Novel Technologies
PSP-Element(e) G-507100-001
DOI 10.1007/978-3-031-47401-9_9
WOS ID 001160722800009
Scopus ID 85180624612
Erfassungsdatum 2024-01-19
[➜Korrektur melden]