Libra

Nowadays we are witnessing widespread adoption of decision-making software with far-reaching societal impact, e.g., in fiels such as social welfare, criminal justice, and even health care. It is not difficult to envision that in the future most of the decisions in society will be delegated to software. As decision-making software becomes more and more widespread, a number of recent cases have evidenced the importance of ensuring software fairness[1][2].

Even software products that we regularly use are biased!
Going forward, decision-making software will be subject to more and more legal regulations as well as administrative audits.

Libra

The goal of the Libra research project is to meet these needs and develop new analyses and tools to reason about and certify fairness of decision-making software.

A prototype static analyzer for certifying fairness of feed-forward neural networks used for classification of tabular data is open-source and available on GitHub.

Completed Projects

  • Abhinandan Pal (Bachelor Student, IIIT Kalyani, India)
    GPU-based Fairness Certification of Neural Networks
    Research Internship (remote), 2022
  • Marco Zanella (PhD Student, Università degli Studi di Padova, Italy)
    Fairness of Decision Tree Ensemble Classifiers
    PhD Internship, École Normale Supérieure, 2020

Publications

. Abstract Interpretation-Based Feature Importance for Support Vector Machines. In VMCAI, 2024.

PDF Project HAL Springer

. Abstract Interpretation-Based Feature Importance for SVMs. CoRR abs/2210.12456, 2022.

PDF Project arXiv

. ReCIPH: Relational Coefficients for Input Partitioning Heuristic. In WFVML, 2022.

Project

. Fair Training of Decision Tree Classifiers. CoRR abs/2101.00909, 2021.

PDF Project arXiv

. Perfectly Parallel Fairness Certification of Neural Networks. CoRR abs/1912.02499, 2019.

PDF Code Project BibTeX arXiv

Talks

Interpretability-Aware Verification of Machine Learning Software
Thursday, April 27, 2023 2:00 PM
Interpretability-Aware Verification of Machine Learning Software
Thursday, March 30, 2023 2:00 PM
An Abstract Interpretation Recipe for Machine Learning Fairness
Wednesday, November 17, 2021 2:00 PM
An Abstract Interpretation Recipe for Machine Learning Fairness
Tuesday, November 9, 2021 2:30 PM
An Abstract Interpretation Recipe for Machine Learning Fairness
Sunday, July 18, 2021 9:00 AM
Perfectly Parallel Fairness Certification of Neural Networks
Wednesday, May 5, 2021 5:00 PM
Perfectly Parallel Fairness Certification of Neural Networks
Wednesday, January 13, 2021
Perfectly Parallel Fairness Certification of Neural Networks
Thursday, June 18, 2020 3:00 PM
Perfectly Parallel Fairness Certification of Neural Networks
Wednesday, June 3, 2020 2:00 PM
Perfectly Parallel Fairness Certification of Neural Networks
Sunday, May 24, 2020 12:30 PM
Perfectly Parallel Fairness Certification of Neural Networks
Friday, May 15, 2020 10:00 AM
Static Analysis of Data Science Software
Wednesday, October 9, 2019 2:00 PM