17 citations
- Aalto UniversityFI6 papers
- University of OuluFI2 papers
- Centre National de la Recherche ScientifiqueFR1 paper
- Czech Technical University in PragueCZ1 paper
- École Nationale Supérieure d'Ingénieurs de CaenFR1 paper
- Google (United States)US1 paper
- GREYCFR1 paper
- Helsinki Institute for Information TechnologyFI1 paper
- Hubei UniversityCN1 paper
- Institut de Recherche en Informatique et Systèmes AléatoiresFR1 paper
- Institut national de recherche en sciences et technologies du numériqueFR1 paper
- Normandie UniversitéFR1 paper
11 papers
FLAME: Taming Backdoors in Federated Learning (Extended Version 1)
Thien Duc Nguyen, Phillip Rieger, Huili Chen +10
Federated Learning (FL) is a collaborative machine learning approach allowing participants to jointly train a model without having to share their private, potentially sensitive loc…
Test Automation Process Improvement in a DevOpsTeam: Experience Report
Yuqing Wang, Maaret Pyhäjärvi, Mika V. Mäntylä
How to successfully conduct test automation process improvement (TAPI) for continuous development, consisting of iterative software development, continuous testing, and delivery, i…
Federated Stochastic Gradient Langevin Dynamics
Khaoula El Mekkaoui, Diego Mesquita, Paul Blomstedt +1
Stochastic gradient MCMC methods, such as stochastic gradient Langevin dynamics (SGLD), employ fast but noisy gradient estimates to enable large-scale posterior sampling. Although…
Towards Practical Private Information Retrieval from MDS Array Codes
Jie Li, David Karpuk, Camilla Hollanti
Private information retrieval (PIR) is the problem of privately retrieving one out of original files from severs, i.e., each individual server learns nothing about the file…
Dynamic hierarchies in temporal directed networks
Nikolaj Tatti
The outcome of interactions in many real-world systems can be often explained by a hierarchy between the participants. Discovering hierarchy from a given directed network can be fo…
Efficient estimation of AUC in a sliding window
Nikolaj Tatti
In many applications, monitoring area under the ROC curve (AUC) in a sliding window over a data stream is a natural way of detecting changes in the system. The drawback is that com…