How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution

no code implementations • 16 Nov 2024 • Jinbo Wang, Ruijin Wang, Fengli Zhang

In this work, based on the key insight that the convergence process of the model is a highly predictable process, we break away from the traditional horizontal solution of defense and innovatively transform the problem of solving the optimal aggregation gradients into a vertical solution problem.

Federated Learning Model Poisoning

Trajectory-User Linking via Variational AutoEncoder

1 code implementation • International Joint Conference on Artificial Intelligence 2018 • Fan Zhou, Qiang Gao, Goce Trajcevski, Kunpeng Zhang, Ting Zhong, Fengli Zhang

Trajectory-User Linking (TUL) is an essential task in Geo-tagged social media (GTSM) applications, enabling personalized Point of Interest (POI) recommendation and activity identification.