Summary of Fairproof : Confidential and Certifiable Fairness For Neural Networks, by Chhavi Yadav et al.
FairProof : Confidential and Certifiable Fairness for Neural Networks
by Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh, Kamalika Chaudhuri
First submitted to arxiv on: 19 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Machine learning models are widely used in societal applications, but the need for confidentiality and privacy leads to concerns about their fairness. To address this, we propose FairProof, a system that uses Zero-Knowledge Proofs (ZKPs) to publicly verify a model’s fairness while maintaining confidentiality. Our approach involves a fairness certification algorithm specifically designed for fully-connected neural networks. We demonstrate FairProof’s feasibility through an implementation in Gnark and provide open-source code. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you want to use a machine learning model to make predictions, but you’re not sure if it’s fair or biased. This is a big problem! To fix this, we created a way to check if a model is fair without knowing what the model actually does. It uses special math called Zero-Knowledge Proofs (ZKPs). We also made an algorithm that works with these ZKPs and tested our idea by building it. Now you can trust that the models are fair even when they’re kept secret. |
Keywords
* Artificial intelligence * Machine learning
