activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Privacy Risks in Time Series Forecasting: User- and Record-Level Membership Inference

Nicolas Johansson, Tobias Olsson, Daniel Nilsson +2

Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time seri…

cs.LG2025

Subgraph Federated Learning via Spectral Methods

Javad Aliakbari, Johan Östman, Ashkan Panahi +1

We consider the problem of federated learning (FL) with graph-structured data distributed across multiple clients. In particular, we address the prevalent scenario of interconnecte…

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.LG2025

Decoupled Subgraph Federated Learning

Javad Aliakbari, Johan Östman, Alexandre Graell i Amat

We address the challenge of federated learning on graph-structured data distributed across multiple clients. Specifically, we focus on the prevalent scenario of interconnected subg…

cs.LG2024

FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregation

Marvin Xhemrishi, Johan Östman, Antonia Wachter-Zeh +1

We propose FedGT, a novel framework for identifying malicious clients in federated learning with secure aggregation. Inspired by group testing, the framework leverages overlapping…

cs.LG2024

Poisoning Attacks on Federated Learning for Autonomous Driving

Sonakshi Garg, Hugo Jönsson, Gustav Kalander +4

Federated Learning (FL) is a decentralized learning paradigm, enabling parties to collaboratively train models while keeping their data confidential. Within autonomous driving, it…