activity
20002020
most citedOn Privacy-Preserving Histograms

14 citations · 48 across the 7 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.LG2020

Outcome Indistinguishability

Cynthia Dwork, Michael P. Kim, Omer Reingold +2

Prediction algorithms assign numbers to individuals that are popularly understood as individual "probabilities" -- what is the probability of 5-year survival after cancer diagnosis…

cs.LG20203 cited

Interpreting Robust Optimization via Adversarial Influence Functions

Zhun Deng, Cynthia Dwork, Jialiang Wang +1

Robust optimization has been widely used in nowadays data science, especially in adversarial training. However, little research has been done to quantify how robust optimization ch…

cs.LG2020

Private Post-GAN Boosting

Marcel Neunhoeffer, Zhiwei Steven Wu, Cynthia Dwork

Differentially private GANs have proven to be a promising approach for generating realistic synthetic data without compromising the privacy of individuals. Due to the privacy-prote…

cs.LG202011 cited

Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations

Zhun Deng, Frances Ding, Cynthia Dwork +4

We investigate the power of censoring techniques, first developed for learning {\em fair representations}, to address domain generalization. We examine {\em adversarial} censoring…

cs.CY2020

Individual Fairness in Pipelines

Cynthia Dwork, Christina Ilvento, Meena Jagadeesan

It is well understood that a system built from individually fair components may not itself be individually fair. In this work, we investigate individual fairness under pipeline com…

cs.LG20203 cited

Abstracting Fairness: Oracles, Metrics, and Interpretability

Cynthia Dwork, Christina Ilvento, Guy N. Rothblum +1

It is well understood that classification algorithms, for example, for deciding on loan applications, cannot be evaluated for fairness without taking context into account. We exami…