Adrià Gascón

Blind Justice: Fairness with Encrypted Sensitive Attributes

2018 · arXiv (Cornell University)

Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive …

Make Some ROOM for the Zeros: Data Sparsity in Secure Distributed Machine Learning.

2019 · IACR Cryptology ePrint Archive

Exploiting data sparsity is crucial for the scalability of many data analysis tasks. However, while there is an increasing interest in efficient secure computation protocols for distributed machine learning, data sparsity has so far not …

Distributed Vector-OLE

2019

We investigate concretely efficient protocols for distributed oblivious linear evaluation over vectors (Vector-OLE). Boyle et al. (CCS 2018) proposed a protocol for secure distributed pseudorandom Vector-OLE generation using sublinear</>communication, but they did not provide an …

Private Summation in the Multi-Message Shuffle Model

2020

The shuffle model of differential privacy (Erlingsson et al. SODA 2019; Cheu et al. EUROCRYPT 2019) and its close relative encode-shuffle-analyze (Bittau et al. SOSP 2017) provide a fertile middle ground between the well-known local …