Privacy-Preserving Distributed Expectation Maximization for Gaussian Mixture Model using Subspace Perturbation

Autor: Li, Qiongxiu, Gundersen, Jaron Skovsted, Tjell, Katrine, Wisniewski, Rafal, Christensen, Mads Græsbøll

Publikováno v: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 4263-4267

Privacy has become a major concern in machine learning. In fact, the federated learning is motivated by the privacy concern as it does not allow to transmit the private data but only intermediate updates. However, federated learning does not always g

Externí odkaz: http://arxiv.org/abs/2209.07833

Privacy Preservation in Epidemic Data Collection

Autor: Tjell, Katrine, Gundersen, Jaron Skovsted, Wisniewski, Rafael

This work is inspired by the outbreak of COVID-19, and some of the challenges we have observed with gathering data about the disease. To this end, we aim to help collect data about citizens and the disease without risking the privacy of individuals.

Externí odkaz: http://arxiv.org/abs/2004.14759

Private Aggregation with Application to Distributed Optimization

Autor: Tjell, Katrine, Wisniewski, Rafal

Publikováno v: Tjell, K & Wisniewski, R 2021, ' Private Aggregation with Application to Distributed Optimization ', IEEE Control Systems Letters, vol. 5, no. 5, 9274412, pp. 1591-1596 . https://doi.org/10.1109/LCSYS.2020.3041611

This letter presents a fully distributed private aggregation protocol that can be employed in dynamical networks where communication is only assumed on a neighbor-to-neighbor basis. The novelty of the scheme is its low overhead in communication and c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::29b2a2b51b4521871a1be76ad1717027
https://vbn.aau.dk/ws/files/433818416/Private_Aggregation_with_Application_to_Distributed_Optimization_.pdf

Secure learning-based MPC via garbled circuit

Autor: Tjell, Katrine, Schlüter, Nils, Binfet, Philipp, Darup, Moritz Schulze

Publikováno v: Tjell, K, Schlüter, N, Binfet, P & Darup, M S 2021, Secure learning-based MPC via garbled circuit . in 2021 IEEE 60th Conference on Decision and Control (CDC) ., 9683540, IEEE, I E E E Conference on Decision and Control. Proceedings, pp. 4907-4914, 2021 60th IEEE Conference on Decision and Control (CDC), Austin, Texas, United States, 14/12/2021 . https://doi.org/10.1109/CDC45484.2021.9683540

Encrypted control seeks confidential controller evaluation in cloud-based or networked systems. Many existing approaches build on homomorphic encryption (HE) that allow simple mathematical operations to be carried out on encrypted data. Unfortunately

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17ba24d4b62872366328d406dcaf8676
https://vbn.aau.dk/da/publications/be9e2950-2640-4564-b39e-9bdc222bcd09