Olya Ohrimenko

Analyzing Information Leakage of Updates to Natural Language Models

S Zanella-Béguelin, L Wutschitz, S Tople, V Rühle, A Paverd, Olga Ohrimenko, B Köpf, M Brockschmidt

Conference Proceedings  |  2020  |  Proceedings of the ACM Conference on Computer and Communications Security

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update th..

PPML'19: Privacy preserving machine learning

B Balle, M Raykova, A Gascón, P Schoppmmann, O Ohrimenko, C Troncoso

Conference Proceedings  |  2019  |  Proceedings of the ACM Conference on Computer and Communications Security

The area of privacy preserving machine learning has been of growing importance in practice, which has lead to an increased interes..

Oblivious sampling algorithms for private data analysis

S Sasy, O Ohrimenko

Conference Proceedings  |  2019  |  Advances in Neural Information Processing Systems

We study secure and privacy-preserving data analysis based on queries executed on samples from a dataset. Trusted execution enviro..

An algorithmic framework for differentially private data analysis on trusted processors

J Allen, B Ding, J Kulkarni, H Nori, O Ohrimenko, S Yekhanin

Conference Proceedings  |  2019  |  Advances in Neural Information Processing Systems

Differential privacy has emerged as the main definition for private data analysis and machine learning. The global model of differ..

Verifying the consistency of remote untrusted services with conflict-free operations

C Cachin, O Ohrimenko

Journal article  |  2018  |  Information and Computation

A group of mutually trusting clients outsources a computation to a remote server, which they do not fully trust and that may be su..

Contamination attacks and mitigation in multi-party machine learning

J Hayes, O Ohrimenko

Conference Proceedings  |  2018  |  Advances in Neural Information Processing Systems

Machine learning is data hungry; the more data a model has access to in training, the more likely it is to perform well at inferen..

Structured Encryption and Leakage Suppression

Seny Kamara, Tarik Moataz, Olga Ohrimenko

Conference Proceedings  |  2018  |  Advances in Cryptology – CRYPTO 2018

Structured encryption (STE) schemes encrypt data structures in such a way that they can be privately queried. One aspect of STE th..

Forward and backward private searchable encryption from constrained cryptographic primitives

R Bost, B Minaud, O Ohrimenko

Conference Proceedings  |  2017  |  Proceedings of the ACM Conference on Computer and Communications Security

Using dynamic Searchable Symmetric Encryption, a user with limited storage resources can securely outsource a database to an untru..

Strong and efficient cache side-channel protection using hardware transactional memory

D Gruss, J Lettner, F Schuster, O Ohrimenko, I Haller, M Costa

Conference Proceedings  |  2017  |  Proceedings of the 26th USENIX Security Symposium

Hash first, argue later: Adaptive verifiable computations on outsourced data

D Fiore, C Fournet, E Ghosh, M Kohlweiss, O Ohrimenko, B Parno

Conference Proceedings  |  2016  |  Proceedings of the ACM Conference on Computer and Communications Security

Proof systems for verifiable computation (VC) have the potential to make cloud outsourcing more trustworthy. Recent schemes enable..