* External authors




Data Poisoning Attacks on Federated Machine Learning

Gan Sun*

Yang Cong*

Jiahua Dong*

Qiang Wang*

Lingjuan Lyu

Ji Liu*

* External authors

IEEE Internet of Things Journal



Federated machine learning which enables resource-constrained node devices (e.g., Internet of Things (IoT) devices, 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 paper 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 multi-task learning framework, which uses a general multi-task learning framework to handle statistical challenges in federated learning setting. The problem of calculating optimal poisoning attacks on federated multi-task learning is formulated as a bilevel program, which is adaptive to arbitrary selection of target nodes and source attacking nodes. We then propose a novel systems-aware optimization method, called as ATTack on Federated Learning (ATFL), 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 datasets demonstrate that when the attackers directly poison the target nodes or indirectly poison the related nodes via using the communication protocol, federated multi-task learning model is sensitive to both poisoning attacks.

Related Publications

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

NeurIPS, 2023
Xiaoxiao Sun*, Nidham Gazagnadou, Vivek Sharma, Lingjuan Lyu, Hongdong Li*, Liang Zheng*

Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally indicate more privacy leakage. Image…

UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition

NeurIPS, 2023
Yuyuan Li*, Chaochao Chen*, Yizhao Zhang*, Weiming Liu*, Lingjuan Lyu, Xiaolin Zheng*, Dan Meng*, Jun Wang*

With growing concerns regarding privacy in machine learning models, regulations have committed to granting individuals the right to be forgotten while mandating companies to develop non-discriminatory machine learning systems, thereby fueling the study of the machine unlearn…

Towards Personalized Federated Learning via Heterogeneous Model Reassembly

NeurIPS, 2023
Jiaqi Wang*, Xingyi Yang*, Suhan Cui*, Liwei Che*, Lingjuan Lyu, Dongkuan Xu*, Fenglong Ma*

This paper focuses on addressing the practical yet challenging problem of model heterogeneity in federated learning, where clients possess models with different network structures. To track this problem, we propose a novel framework called pFedHR, which leverages heterogeneo…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.