Papers · Proving properties · FairProof

FairProof

FairProof: Confidential and Certifiable Fairness for Neural Networks

Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh, Kamalika Chaudhuri

Venue
ICML 2024
Date
2024-02-19
Proof system
Gnark
Numbers from
primary
Open source
yes
Paper
https://arxiv.org/abs/2402.12572

Notes

Publicly verify a model is fair while keeping weights confidential. Author web worth noting: Roy Chowdhury also wrote EIFFeL, and Boneh co-authored Prio -- the same people keep appearing across the verifiable-FL and property-proving clusters.

Our reading

Citation neighbourhood

Builds on
  • none recorded
Cited by, in this corpus
  • none recorded

Edges are a proxy: paper A's text mentions B anywhere (body or bibliography). See the full graph.

Discussed in

A claim about a model, not about a computationThe prior surveys, and where we disagree with them
Other recorded fields
property_proven: Local fairness certificate for fully-connected neural networks