Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage

On the privacy risks of model explanations

Original

Shokri, R., Strobel, M., and Zick, Y · 1907

Earlier work this paper cites.

Differentially private support vector machines

Original

Chaudhuri, K., Monteleoni, C., and Sarwate, A. D · 2009

Earlier work this paper cites.

The algorithmic foundations of differential privacy

Dwork, C. and Roth, A · 2014

Earlier work this paper cites.

Deep learning with differential privacy

Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., and Zhang, L · 2016

Earlier work this paper cites.

UCI machine learning repository, 2017

Dua, D. and Graff, C · 2017

Earlier work this paper cites.

Counterfactual explanations without opening the black box: Automated decisions and the gdpr

Wachter, S., Mittelstadt, B., and Russell, C · 2017

Cited alongside, same era.

The unintended consequences of overfitting: Training data inference attacks

Original

Yeom, S., Fredrikson, M., and Jha, S · 2017

Cited alongside, same era.

Diffprivlib: the IBM differential privacy library

Holohan, N., Braghin, S., Mac Aonghusa, P., and Levacher, K · 2019

Cited alongside, same era.

Evaluating differentially private machine learning in practice, 2019

Jayaraman, B. and Evans, D · 2019

Cited alongside, same era.

Mnist dataset, 2019

Khodabakhsh, H., LeCun, Y., Cortes, C., and Burges, C. J · 2019

Cited alongside, same era.

Explainable machine learning challenge

FICO Community

Cited in the paper.

Model reconstruction from model explanations

Milli, S., Schmidt, L., Dragan, A. D., and Hardt, M · 2019

Later among the works it cites.

Transparency: Motivations and challenges

Original

Weller, A · 2019

Later among the works it cites.

Model extraction from counterfactual explanations

Original

Aïvodji, U., Bolot, A., and Gambs, S · 2020

Later among the works it cites.

Membership inference attacks from first principles

Original

Carlini, N., Chien, S., Nasr, M., Song, S., Terzis, A., and Tramèr, F · 2021

Later among the works it cites.

On the privacy risks of algorithmic recourse

Original

Pawelczyk, M., Lakkaraju, H., and Neel, S · 2022

Later among the works it cites.