PoPETs Proceedings
Volume 2025 Volume 2024 Volume 2023 Volume 2022 Volume 2021 Volume 2020 Volume 2019 Volume 2018 Volume 2017 Volume 2016 Volume 2015 Privacy Enhancing Technologies …
SecureNN: 3-Party Secure Computation for Neural Network Training
Volume: 2019 Issue: 3 Pages: 26–49 DOI: Download PDF Abstract: Neural Networks (NN) provide a powerful method for machine learning training and inference. To effectively train, it is …
Keywords: machine learning; privacy; inference attacks DOI 10.2478/popets-2019-0008 Received 2018-05-31; revised 2018-09-15; accepted 2018-09-16.
Editors’ Introduction DOI 10.2478/popets-2019-0001 ted to the annual Privacy En-hancing Technologies Symposium (PETS). Recognizing the need to increase the free, public …
PoPETs Proceedings — Reducing Metadata Leakage from …
Volume: 2019 Issue: 4 Pages: 6–33 DOI: Download PDF Abstract: Most encrypted data formats leak metadata via their plaintext headers, such as format version, encryption schemes used, …
Keywords: Secure Multi-Party Computation, Privacy-preserving deep learning DOI 10.2478/popets-2019-0035 Received 2018-11-30; revised 2019-03-15; accepted 2019-03-16.
PoPETs Proceedings — Encrypted Databases for Differential Privacy
Volume: 2019 Issue: 3 Pages: 170–190 DOI: Download PDF Abstract: The problem of privatizing statistical databases is a well-studied topic that has culminated with the notion of differential …
Proceedings on Privacy Enhancing Technologies ; 2019 (3):370–388 Dhinakaran Vinayagamurthy*, Alexey Gribov, and Sergey Gorbunov
StealthDB: a Scalable Encrypted Database with Full SQL Query …
Volume: 2019 Issue: 3 Pages: 370–388 DOI: https://doi.org/10.2478/popets-2019-0052 Download PDF Abstract: Encrypted database systems provide a great method for protecting sensitive …
Private Evaluation of Decision Trees using Sublinear Cost
Volume: 2019 Issue: 1 Pages: 266–286 DOI: Download PDF Abstract: Decision trees are widespread machine learning models used for data classification and have many applications …