Show simple item record

dc.contributor.author
Fischer, Marc
dc.contributor.author
Baader, Maximilian
dc.contributor.author
Vechev, Martin
dc.contributor.editor
Larochelle, Hugo
dc.contributor.editor
Ranzato, Marc'Aurelio
dc.contributor.editor
Hadsell, Raia
dc.contributor.editor
Balcan, Maria F.
dc.contributor.editor
Lin, H.
dc.date.accessioned
2021-07-21T07:47:48Z
dc.date.available
2021-01-25T15:21:30Z
dc.date.available
2021-01-26T06:19:25Z
dc.date.available
2021-03-18T09:31:07Z
dc.date.available
2021-07-21T07:47:48Z
dc.date.issued
2021
dc.identifier.isbn
978-1-7138-2954-6
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/465427
dc.identifier.doi
10.3929/ethz-b-000465427
dc.description.abstract
Fair representation learning provides an effective way of enforcing fairness constraints without compromising utility for downstream users. A desirable family of such fairness constraints, each requiring similar treatment for similar individuals, is known as individual fairness. In this work, we introduce the first method thatenables data consumers to obtain certificates of individualfairness for existing andnew data points. The key idea is to map similar individuals toclose latent representations and leverage this latent proximity to certify individual fairness. That is, our method enables the data producer to learn and certify a representation where for a data point all similar individuals are at ℓ∞-distance at most epsilon, thus allowing data consumers to certify individual fairness by proving epsilon-robustness of their classifier. Our experimental evaluation on five real-world datasets and several fairnessconstraints demonstrates the expressivity and scalability of our approach.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Curran
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.title
Certified Defense to Image Transformations via Randomized Smoothing
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2020
ethz.book.title
Advances in Neural Information Processing Systems 33
en_US
ethz.pages.start
8404
en_US
ethz.pages.end
8417
en_US
ethz.size
24 p. updated version
en_US
ethz.version.deposit
updatedVersion
en_US
ethz.event
34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)
en_US
ethz.event.location
Online
en_US
ethz.event.date
December 6-12, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.publication.place
Red Hook, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02664 - Inst. f. Programmiersprachen u. -systeme / Inst. Programming Languages and Systems::03948 - Vechev, Martin / Vechev, Martin
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02664 - Inst. f. Programmiersprachen u. -systeme / Inst. Programming Languages and Systems::03948 - Vechev, Martin / Vechev, Martin
en_US
ethz.identifier.url
https://papers.nips.cc/paper/2020/hash/5fb37d5bbdbbae16dea2f3104d7f9439-Abstract.html
ethz.date.deposited
2021-01-25T15:21:37Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-03-18T09:31:19Z
ethz.rosetta.lastUpdated
2022-03-29T10:33:43Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Certified%20Defense%20to%20Image%20Transformations%20via%20Randomized%20Smoothing&rft.date=2021&rft.spage=8404&rft.epage=8417&rft.au=Fischer,%20Marc&Baader,%20Maximilian&Vechev,%20Martin&rft.isbn=978-1-7138-2954-6&rft.genre=proceeding&rft.btitle=Advances%20in%20Neural%20Information%20Processing%20Systems%2033
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record