Search Results for author: Apostolos Pyrgelis

Found 7 papers, 3 papers with code

SoK: Privacy-Preserving Collaborative Tree-based Model Learning

no code implementations16 Mar 2021 Sylvain Chatel, Apostolos Pyrgelis, Juan Ramon Troncoso-Pastoriza, Jean-Pierre Hubaux

Tree-based models are among the most efficient machine learning techniques for data mining nowadays due to their accuracy, interpretability, and simplicity.

BIG-bench Machine Learning Privacy Preserving

POSEIDON: Privacy-Preserving Federated Neural Network Learning

no code implementations1 Sep 2020 Sinem Sav, Apostolos Pyrgelis, Juan R. Troncoso-Pastoriza, David Froelicher, Jean-Philippe Bossuat, Joao Sa Sousa, Jean-Pierre Hubaux

In this paper, we address the problem of privacy-preserving training and evaluation of neural networks in an $N$-party, federated learning setting.

Federated Learning Privacy Preserving

Privacy and Integrity Preserving Computations with CRISP

1 code implementation8 Jul 2020 Sylvain Chatel, Apostolos Pyrgelis, Juan R. Troncoso-Pastoriza, Jean-Pierre Hubaux

Service providers are interested in verifying the integrity of the users' data to improve their services and obtain useful knowledge for their business.

Cryptography and Security

On Collaborative Predictive Blacklisting

1 code implementation5 Oct 2018 Luca Melis, Apostolos Pyrgelis, Emiliano De Cristofaro

Unfortunately, however, research on CPB has only focused on increasing the number of predicted attacks but has not considered the impact on false positives and false negatives.

Cryptography and Security

Privacy-Friendly Mobility Analytics using Aggregate Location Data

no code implementations21 Sep 2016 Apostolos Pyrgelis, Emiliano De Cristofaro, Gordon Ross

Location data can be extremely useful to study commuting patterns and disruptions, as well as to predict real-time traffic volumes.

Privacy Preserving Time Series +1

Building and Measuring Privacy-Preserving Predictive Blacklists

no code implementations13 Dec 2015 Luca Melis, Apostolos Pyrgelis, Emiliano De Cristofaro

(Withdrawn) Collaborative security initiatives are increasingly often advocated to improve timeliness and effectiveness of threat mitigation.

Privacy Preserving

Cannot find the paper you are looking for? You can Submit a new open access paper.