An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategies

By David Enthoven, Zaid Al-Ars. 2020

60 citations recorded by the source corpus.

With the increased attention and legislation for data-privacy, collaborative machine learning (ML) algorithms are being developed to ensure the protection of private data used for processing. Federated learning (FL) is the most popular of these methods, which provides privacy preservation by facilitating collaborative training of a shared model without the need to exchange any private data with a centralized server. Rather, an abstraction of the data in the form of a machine learning model update is sent. Recent studies showed that such model updates may still very well leak private information and thus more structured risk assessment is needed. In this paper, we analyze existing vulnerabilities of FL and subsequently perform a literature review of the possible attack methods targetingFL privacy protection capabilities. These attack methods are then categorized by a basic taxonomy. Additionally, we provide a literature study of the most recent defensive strategies and algorithms for FL aimed to overcome these attacks. These defensive strategies are categorized by their respective underlying defence principle. The paper concludes that the application of a single defensive strategy is not enough to provide adequate protection to all available attack methods.

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

1. Murali Annavaram
2. Qiang Yang
3. Chaoyang He
4. Yang Liu
5. S. Avestimehr
6. Jiankun Hu
7. Yanming Zhu
8. Xuefei Yin

Citations in the corpus

• FedML: A Research Library and Benchmark for Federated Machine Learning (2020, background): “…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, 28, 29, 30,…”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, background): “The inference attacks can be divided into four categories [47]: • The inference of class representatives aims to generate representative samples, which are not real data instances of training datasets but can be used to study sensitive information about the training datasets [53, 75, 192].”
• Federated Learning in Edge Computing: A Systematic Survey (2022, methodology): “Moreover, Lyu et al. [86] presented a survey paper focusing on the security threats and vulnerability challenges in FL systems; furthermore, the authors of [87] summarized the most used defense strategies in FL.”
• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges (2022, background): “These surveys lack of an holistic view of FL and the review of the defences against adversarial attacks, because of the following reasons: (1) most of them are only focused on one kind of adversarial attacks, namely there are surveys reviewing attacks to the federated model [18, 19, 20] or privacy a”