Abstract

The abstract summarizes a Proof of Concept (PoC) of measuring the impact of stealth data poisoning with a fixed magnitude on a federated machine learning model. The model is created in Tensorflow Lite and is used to predict the strength of the mobile network. It operates on four physical mobile devices running the Android operating system, each representing a different mobile network. The experiment demonstrates the hardware and software setup (including limitations applied), initial results of accuracy and loss measurements, and indicates potential improvements for the future.

Recommended Citation

Kuczynski, M.(2026). Simulation of a Fixed-Magnitude Data Poisoning Attack in a Federated Learning Distributed Model. In M. Valenta, B. Mannová, R. Pergl, A. Przybylek, M. Lang, H. Linger, C. Schneider, N. Iivari, & E. Insfran (Eds.), Making ISD Sustainable: Reloaded with AI and Automation (ISD2026 Proceedings). Prague, Czech Republic: Czech Technical University in Prague. ISBN: 978-80-01-07585-2. https://doi.org/10.62036/ISD.2026.97

Paper Type

Poster

DOI

10.62036/ISD.2026.97

Share

COinS
 

Simulation of a Fixed-Magnitude Data Poisoning Attack in a Federated Learning Distributed Model

The abstract summarizes a Proof of Concept (PoC) of measuring the impact of stealth data poisoning with a fixed magnitude on a federated machine learning model. The model is created in Tensorflow Lite and is used to predict the strength of the mobile network. It operates on four physical mobile devices running the Android operating system, each representing a different mobile network. The experiment demonstrates the hardware and software setup (including limitations applied), initial results of accuracy and loss measurements, and indicates potential improvements for the future.