Perfectly Parallel Fairness Certification of Neural Networks
Preprint
Abstract
Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the training data. The development of tools and techniques for certifying fairness of these models or describing their biased behavior is, therefore, critical. In this paper, we propose a perfectly parallel static analysis for certifying causal fairness of feed-forward neural networks used for classification of tabular data. When certification succeeds, our approach provides definite guarantees, otherwise, it describes and quantifies the biased behavior. We design the analysis to be sound, in practice also exact, and configurable in terms of scalability and precision, thereby enabling pay-as-you-go certification. We implement our approach in an open-source tool and demonstrate its effectiveness on models trained with popular datasets.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification2019
- An Abstract Interpretation Framework for Input Data Usage2018
- Repairing Decision-Making Programs Under Uncertainty2017
- Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks2017
- Safety Verification of Deep Neural Networks2017
- Robustness Analysis of Finite Precision Implementations2013
- The Zonotope Abstract Domain Taylor1+2009
- A Sound Floating-Point Polyhedra Abstract Domain2008
- Symbolic Methods to Enhance the Precision of Numerical Abstract Domains2005
- Relational Abstract Domains for the Detection of Floating-Point Run-Time Errors2004