Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
Jayadev Naram, Fredrik Hellström, Ziming Wang +2
In many scenarios of practical interest, labeled data from a target distribution are scarce while labeled data from a related source distribution are abundant. One particular setti…
cs.LG2024
Secure Aggregation is Not Private Against Membership Inference Attacks
Khac-Hoang Ngo, Johan Östman, Giuseppe Durisi +1
Secure aggregation (SecAgg) is a commonly-used privacy-enhancing mechanism in federated learning, affording the server access only to the aggregate of model updates while safeguard…