Data Poisoning Attacks on Federated Machine Learning

Gan Sun, Yang Cong, Jiahua Dong, Qiang Wang, Lingjuan Lyu, Ji Liu

Abstract: Federated machine learning which enables resource-constrained node devices (e.g., Internet of Things (IoT) devices and smartphones) to establish a knowledge-shared model while keeping the raw data local, could provide privacy preservation, and economic benefit by designing an effective communication protocol. However, this communication protocol can be adopted by attackers to launch data poisoning attacks for different nodes, which has been shown as a big threat to most machine learning models. Therefore, we in this article intend to study the model vulnerability of federated machine learning, and even on IoT systems. To be specific, we here attempt to attacking a popular federated multitask learning framework, which uses a general multitask learning framework to handle statistical challenges in the federated learning setting. The problem of calculating optimal poisoning attacks on federated multitask learning is formulated as a bilevel program, which is adaptive to the arbitrary selection of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">target</i> nodes and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">source attacking</i> nodes. We then propose a novel systems-aware optimization method, called as attack on federated learning (AT <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> FL), to efficiently derive the implicit gradients for poisoned data, and further attain optimal attack strategies in the federated machine learning. This is an earlier work, to our knowledge, that explores attacking federated machine learning via data poisoning. Finally, experiments on several real-world data sets demonstrate that when the attackers directly poison the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">target</i> nodes or indirectly poison the related nodes via using the communication protocol, the federated multitask learning model is sensitive to both poisoning attacks.