3 papers
cs.LG2025
Perfectly-Private Analog Secure Aggregation in Federated Learning
Delio Jaramillo-Velez, Charul Rajput, Ragnar Freij-Hollanti +2
In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model. To address the risk o…
cs.LG2025
Practical Bayes-Optimal Membership Inference Attacks
Marcus Lassila, Johan Östman, Khac-Hoang Ngo +1
We develop practical and theoretically grounded membership inference attacks (MIAs) against both independent and identically distributed (i.i.d.) data and graph-structured data. Bu…
cs.IT2025
Soft-Decision Decoding for LDPC Code-Based Quantitative Group Testing
Marvin Xhemrishi, Johan Östman, Alexandre Graell i Amat
We consider the problem of identifying defective items in a population with non-adaptive quantitative group testing. For this scenario, Mashauri et al. recently proposed a low-dens…