Efficient Counterexample-Guided Fairness Verification and Repair of Neural Networks Using Satisfiability Modulo Convex Programming

Fayyazi, Arya; Xiao, Yifeng; Nuzzo, Pierluigi; Pedram, Massoud

doi:10.24963/ijcai.2025/42

Efficient Counterexample-Guided Fairness Verification and Repair of Neural Networks Using Satisfiability Modulo Convex Programming

Arya Fayyazi, Yifeng Xiao, Pierluigi Nuzzo, Massoud Pedram

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 367-375.

https://doi.org/10.24963/ijcai.2025/42

Keywords

AI Ethics, Trust, Fairness: ETF: Fairness and diversity
AI Ethics, Trust, Fairness: ETF: Bias
Constraint Satisfaction and Optimization: CSO: Constraint satisfaction
Constraint Satisfaction and Optimization: CSO: Satisfiabilty

Abstract

Ensuring fairness is essential for ethical decision-making in various domains. Informally, a neural network is considered fair if and only if it treats similar individuals similarly in a given task.

We introduce FaVeR (Fairness Verification and Repair), a framework for efficiently verifying and repairing pre-trained neural networks with respect to individual fairness properties.

FaVeR ensures fairness via iterative search of high-sensitivity neurons and backward adjustment of their weights, guided by counterexamples generated from fairness verification using satisfiability modulo convex programming. By addressing fairness at the neuron level, FaVeR minimizes the impact of neural network repair on the overall performance. Experimental evaluations on common fairness datasets show that FaVeR achieves a 100% fairness repair rate across all models, with accuracy reduction of less than 2.27%. Moreover, its significantly lower average runtime makes it suitable for practical applications.

Arya Fayyazi, Yifeng Xiao, Pierluigi Nuzzo, and Massoud Pedram. 2025. Efficient Counterexample-Guided Fairness Verification and Repair of Neural Networks Using Satisfiability Modulo Convex Programming. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 367–375. https://doi.org/10.24963/ijcai.2025/42

@inproceedings{ijcai2025p42,
  title     = {Efficient Counterexample-Guided Fairness Verification and Repair of Neural Networks Using Satisfiability Modulo Convex Programming},
  author    = {Fayyazi, Arya and Xiao, Yifeng and Nuzzo, Pierluigi and Pedram, Massoud},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {367--375},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/42},
  url       = {https://doi.org/10.24963/ijcai.2025/42},
}

TY  - CPAPER
TI  - Efficient Counterexample-Guided Fairness Verification and Repair of Neural Networks Using Satisfiability Modulo Convex Programming
AU  - Fayyazi, Arya
AU  - Xiao, Yifeng
AU  - Nuzzo, Pierluigi
AU  - Pedram, Massoud
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 367
EP  - 375
DO  - 10.24963/ijcai.2025/42
UR  - https://doi.org/10.24963/ijcai.2025/42
ER  -