Understanding Distributed Poisoning Attack in Federated Learning

Cao, Di; Chang, Shan; Lin, Zhijian; Li, Guohua; Sun, Deqing

doi:10.1109/icpads47876.2019.00042

Cited by 179 publications

(73 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One case is a type of inference attack (Krumm, 2007), which is designed to examine the privacy protection effectiveness of our framework, especially for location privacy. The other is a type of distributed poisoning attack (Cao, Chang, Lin, Liu, & Sun, 2019), designed to examine the robustness of the federated learning model, that is, how stable the recommendation accuracy is when under poisoning attack.…”

Section: Experiments and Resultsmentioning

confidence: 99%

A privacy‐preserving framework for location recommendation using decentralized collaborative machine learning

Rao

Gao

et al. 2021

Transactions in GIS

View full text Add to dashboard Cite

The nowadays ubiquitous location‐aware mobile devices have contributed to the rapid growth of individual‐level location data. Such data are usually collected by location‐based service platforms as training data to improve their predictive models' performance, but the collection of such data may raise public concerns about privacy issues. In this study, we introduce a privacy‐preserving location recommendation framework based on a decentralized collaborative machine learning approach: federated learning. Compared with traditional centralized learning frameworks, we keep users' data on their own devices and train the model locally so that their data remain private. The local model parameters are aggregated and updated through secure multiple‐party computation to achieve collaborative learning among users while preserving privacy. Our framework also integrates information about transportation infrastructure, place safety, and flow‐based spatial interaction to further improve recommendation accuracy. We further design two attack cases to examine the privacy protection effectiveness and robustness of the framework. The results show that our framework achieves a better balance on the privacy–utility trade‐off compared with traditional centralized learning methods. The results and ensuing discussion offer new insights into privacy‐preserving geospatial artificial intelligence and promote geoprivacy in location‐based services.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

A privacy‐preserving framework for location recommendation using decentralized collaborative machine learning

Rao

Gao

et al. 2021

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…They use a variant of Multi-Party Computation (MPC) to improve usability under existence of malicious clients. In [31], Cao et al analyze the effect of poisoned data and the number of attackers on the performance of distributed poisoning attacks, and propose a scheme to drop poisoned local models during the training of global model. Gao et al [32] introduce a privacy-preserving framework for heterogeneous federated transfer learning, which uses an end-to-end secure multi-party learning approach.…”

Section: B Privacy and Security Of Flmentioning

confidence: 99%

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Yoshinaga

et al. 2020

IEEE Open J. Comput. Soc.

284

106

View full text Add to dashboard Cite

show abstract

“…Poisoning attacks can occur during the training period and are primarily aimed at availability or integrity of the data. Generally, there are two main approaches to generate poisoned attacks, namely: label-flipping [22] and backdoor [23]. In this paper, we mainly focus on labelflipping where an adversary modifies a small number of examples/training data and maintains the characteristics of the data unchanged to degrade the performance of the model.…”

Section: A Learning Modelmentioning

confidence: 99%

“…Data poisoning: According to work in [28,22], when launching targeted poisoning attacks (i.e., label flipping attack) on a handwritten digits classifier, the easiest and hardest source and target label pairs are (6,2) and (8,4), respectively. Accordingly, we study both targeted labels.…”

Section: A Experimental Setupmentioning

confidence: 99%

Data-Quality Based Scheduling for Federated Edge Learning

Taïk

Moudoud

Cherkaoui

2021

2021 IEEE 46th Conference on Local Computer Networks (LCN)

View full text Add to dashboard Cite

FEderated Edge Learning (FEEL) has emerged as a leading technique for privacy-preserving distributed training in wireless edge networks, where edge devices collaboratively train machine learning (ML) models with the orchestration of a server. However, due to frequent communication, FEEL needs to be adapted to the limited communication bandwidth. Furthermore, the statistical heterogeneity of local datasets' distributions, and the uncertainty about the data quality pose important challenges to the training's convergence. Therefore, a meticulous selection of the participating devices and an analogous bandwidth allocation are necessary. In this paper, we propose a data-quality based scheduling (DQS) algorithm for FEEL. DQS prioritizes reliable devices with rich and diverse datasets. In this paper, we define the different components of the learning algorithm and the data-quality evaluation. Then, we formulate the device selection and the bandwidth allocation problem. Finally, we present our DQS algorithm for FEEL, and we evaluate it in different data poisoning scenarios.

show abstract

Understanding Distributed Poisoning Attack in Federated Learning

Cited by 179 publications

References 5 publications

A privacy‐preserving framework for location recommendation using decentralized collaborative machine learning

A privacy‐preserving framework for location recommendation using decentralized collaborative machine learning

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Data-Quality Based Scheduling for Federated Edge Learning

Contact Info

Product

Resources

About