Author

Johannes Bjerva

h-index 0 View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning

The results show that colluding semi-honest nodes can recover the original local updates of honest nodes, enabling downstream reconstruction of private training data, and demonstrate that SA alone does not guarantee privacy in DFL when local aggregation induces asymmetric observations.

Wen-Rui Yu, Chang-Long Ji, Johannes Bjerva et al. · 0 citations

Conference Open access 2026

A Hierarchical Evaluation Framework for LLM-driven Threat Modelling Tools

A systematic evaluation framework for LLM-driven threat modelling tools to support tool selection, observing the general LLM-integration, governance risks, and allowing for comparison of tool output is introduced.

Josephine Bakka, A. Brandhøj, T. Bøgedal et al. · International Conference on... · 0 citations