一句话：用抽象与公平性引导的迭代精化，对深度神经网络进行个体公平性的形式化认证，并能量化可证明公平个体的比例。
该论文研究深度神经网络（DNN）的个体公平性形式化认证问题：要求仅在受法律保护的属性（如性别、种族）上不同的两个个体得到相同对待。已有技术在 DNN 规模与输入维度增大时往往面临可扩展性或精度不足的问题。作者提出对基于符号区间的 DNN 分析施加抽象，并由公平性性质引导迭代精化，从而缓解上述瓶颈；同时把该方法从传统的定性认证提升到定量认证，即计算分类输出可被证明公平的个体所占百分比，而不仅仅是判定网络是否公平。作者实现了该工具并在四个公平性研究常用数据集上训练的 DNN 上进行评估，实验表明其精度优于当前最先进技术，且速度快数个数量级。
We propose a method for formally certifying and quantifying individual fairness of deep neural networks (DNN). Individual fairness guarantees that any two individuals who are identical except for a legally protected attribute (e.g., gender or race) receive the same treatment. While there are existing techniques that provide such a guarantee, they tend to suffer from lack of scalability or accuracy as the size and input dimension of the DNN increase. Our method overcomes this limitation by applying abstraction to a symbolic interval based analysis of the DNN followed by iterative refinement guided by the fairness property. Furthermore, our method lifts the symbolic interval based analysis from conventional qualitative certification to quantitative certification, by computing the percentage of individuals whose classification outputs are provably fair, instead of merely deciding if the DNN is fair. We have implemented our method and evaluated it on deep neural networks trained on four popular fairness research datasets. The experimental results show that our method is not only more accurate than state-of-the-art techniques but also several orders-of-magnitude faster.
DOI 原文 ·
@inproceedings{paperbot8773,
title = {Fairquant: Certifying and Quantifying Fairness of Deep Neural Networks},
author = {Brian Hyeongseok Kim and Jingbo Wang and Chao Wang},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00016}
}