FairZK

FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge

Tianyu Zhang, Shen Dong, O. Deniz Kose, Yanning Shen, Yupeng Zhang

Venue
IEEE S&P 2025
Date
2025-05-12
Affiliation
UIUC / UC Irvine / Shanghai Jiao Tong
Numbers from
primary
Paper
https://arxiv.org/abs/2505.07997

Reported benchmarks

modelparamsproving time sspeedup vs priornote
DNN47M3433.1–1789First system to prove fairness at 47M parameters.

Notes

The scalability unlock: derives fairness bounds from MODEL PARAMETERS plus aggregated input statistics, rather than by proving inference over a specific dataset. That is why it reaches 47M params where inference-based fairness proofs cannot. Yupeng Zhang also co-authored zkCNN and DeepProve.

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

Other recorded fields
property_proven: Group fairness of logistic regression and DNNs