Can Differential Privacy Hinder Poisoning Attack Detection in Federated Learning?
Chaitanya Aggarwal, Divya G. Nair, Jafar Aco Mohammadi, Jyothisha J. Nair, Jörg Ott · Journal of Sensor and Actuator Networks · 2025
We consider the problem of data poisoning attack detection in a federated learning (FL) setup with differential privacy (DP). Local DP in FL ensures that privacy leakage caused by shared gradients is controlled by adding randomness to the process. We are interested in studying the effect of the Gaussian mechanism in the detection of different data poisoning attacks. As the additive noise from DP could hide poisonous data, the effectiveness of detection algorithms should be analyzed. We present two poisonous data detection algorithms and one malicious client identification algorithm. For the latter, we show that the effect of DP noise decreases as the size of the neural network increases. We further demonstrate this effect alongside the performance of these algorithms on three publicly available datasets.