A Framework for Evaluating Gradient Leakage Attacks in Federated Learning

By Wenqi Wei, Ling Liu, Margaret L. Loper, Ka-Ho Chow, Mehmet Emre Gursoy, Stacey Truex, Yanzhao Wu. 2020

172 citations recorded by the source corpus.

Federated learning (FL) is an emerging distributed machine learning framework for collaborative model training with a network of clients (edge devices). FL offers default client privacy by allowing clients to keep their sensitive data on local devices and to only share local training parameter updates with the federated server. However, recent studies have shown that even sharing local parameter updates from a client to the federated server may be susceptible to gradient leakage attacks and intrude the client privacy regarding its training data. In this paper, we present a principled framework for evaluating and comparing different forms of client privacy leakage attacks. We first provide formal and experimental analysis to show how adversaries can reconstruct the private local training data by simply analyzing the shared parameter update from local training (e.g., local gradient or weight update vector). We then analyze how different hyperparameter configurations in federated learning and different settings of the attack algorithm may impact on both attack effectiveness and attack cost. Our framework also measures, evaluates, and analyzes the effectiveness of client privacy leakage attacks under different gradient compression ratios when using communication efficient FL protocols. Our experiments also include some preliminary mitigation strategies to highlight the importance of providing a systematic attack evaluation framework towards an in-depth understanding of the various forms of client privacy leakage threats in federated learning and developing theoretical foundations for attack mitigation.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

FedML: A Research Library and Benchmark for Federated Machine Learning (2020, background): “…research focuses on developing new adversarial attack and defense techniques to make federated learning robust [13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 22], and proposing methods such as differential privacy (DP) and secure multiparty computation (SMPC) to protect privacy [25, 26, 27,…”
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning (2021, methodology): “Based on [Geiping et al., 2020], [Wei et al., 2020] analyzes how different conﬁgurations in the training may affect attack effectiveness.”
Self-supervised Cross-silo Federated Neural Architecture Search (2021, background): “devices: Usually, the manual architectures rely heavily on researchers’ knowledge and are often too complex to be adaptively deployed onto different types of resource constrained devices; • Unacceptable communication complexity: Training VFL algorithms often require expensive communication overhead ”