Skip to Main content Skip to Navigation
Conference papers

Reduced Products of Abstract Domains for Fairness Certification of Neural Networks

Denis Mazzucato 1 Caterina Urban 1 
1 ANTIQUE - Analyse Statique par Interprétation Abstraite
DI-ENS - Département d'informatique - ENS Paris, Inria de Paris
Abstract : We present Libra, an open-source abstract interpretationbased static analyzer for certifying fairness of ReLU neural network classifiers for tabular data. Libra combines a sound forward pre-analysis with an exact backward analysis that leverages the polyhedra abstract domain to provide definite fairness guarantees when possible, and to otherwise quantify and describe the biased input space regions. The analysis is configurable in terms of scalability and precision. We equipped Libra with new abstract domains to use in the pre-analysis, including a generic reduced product domain construction, as well as search heuristics to find the best analysis configuration. We additionally set up the backward analysis to allow further parallelization. Our experimental evaluation demonstrates the effectiveness of the approach on neural networks trained on a popular dataset in the fairness literature.
Document type :
Conference papers
Complete list of metadata
Contributor : Denis Mazzucato Connect in order to contact the contributor
Submitted on : Friday, September 17, 2021 - 4:43:29 PM
Last modification on : Wednesday, June 8, 2022 - 12:50:03 PM
Long-term archiving on: : Saturday, December 18, 2021 - 7:07:46 PM


Files produced by the author(s)


  • HAL Id : hal-03348036, version 1



Denis Mazzucato, Caterina Urban. Reduced Products of Abstract Domains for Fairness Certification of Neural Networks. 28th Static Analysis Symposium (SAS 2021), Oct 2021, Chicago, United States. ⟨hal-03348036⟩



Record views


Files downloads