Free-rider Attacks on Model Aggregation in Federated Learning

Yann Fraboni, Richard Vidal, Marco Lorenzi
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:1846-1854, 2021.

Abstract

Free-rider attacks against federated learning consist in dissimulating participation to the federated learning process with the goal of obtaining the final aggregated model without actually contributing with any data. This kind of attacks are critical in sensitive applications of federated learning when data is scarce and the model has high commercial value. We introduce here the first theoretical and experimental analysis of free-rider attacks on federated learning schemes based on iterative parameters aggregation, such as FedAvg or FedProx, and provide formal guarantees for these attacks to converge to the aggregated models of the fair participants. We first show that a straightforward implementation of this attack can be simply achieved by not updating the local parameters during the iterative federated optimization. As this attack can be detected by adopting simple countermeasures at the server level, we subsequently study more complex disguising schemes based on stochastic updates of the free-rider parameters. We demonstrate the proposed strategies on a number of experimental scenarios, in both iid and non-iid settings. We conclude by providing recommendations to avoid free-rider attacks in real world applications of federated learning, especially in sensitive domains where security of data and models is critical.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-fraboni21a, title = { Free-rider Attacks on Model Aggregation in Federated Learning }, author = {Fraboni, Yann and Vidal, Richard and Lorenzi, Marco}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {1846--1854}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/fraboni21a/fraboni21a.pdf}, url = {https://proceedings.mlr.press/v130/fraboni21a.html}, abstract = { Free-rider attacks against federated learning consist in dissimulating participation to the federated learning process with the goal of obtaining the final aggregated model without actually contributing with any data. This kind of attacks are critical in sensitive applications of federated learning when data is scarce and the model has high commercial value. We introduce here the first theoretical and experimental analysis of free-rider attacks on federated learning schemes based on iterative parameters aggregation, such as FedAvg or FedProx, and provide formal guarantees for these attacks to converge to the aggregated models of the fair participants. We first show that a straightforward implementation of this attack can be simply achieved by not updating the local parameters during the iterative federated optimization. As this attack can be detected by adopting simple countermeasures at the server level, we subsequently study more complex disguising schemes based on stochastic updates of the free-rider parameters. We demonstrate the proposed strategies on a number of experimental scenarios, in both iid and non-iid settings. We conclude by providing recommendations to avoid free-rider attacks in real world applications of federated learning, especially in sensitive domains where security of data and models is critical. } }
Endnote
%0 Conference Paper %T Free-rider Attacks on Model Aggregation in Federated Learning %A Yann Fraboni %A Richard Vidal %A Marco Lorenzi %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-fraboni21a %I PMLR %P 1846--1854 %U https://proceedings.mlr.press/v130/fraboni21a.html %V 130 %X Free-rider attacks against federated learning consist in dissimulating participation to the federated learning process with the goal of obtaining the final aggregated model without actually contributing with any data. This kind of attacks are critical in sensitive applications of federated learning when data is scarce and the model has high commercial value. We introduce here the first theoretical and experimental analysis of free-rider attacks on federated learning schemes based on iterative parameters aggregation, such as FedAvg or FedProx, and provide formal guarantees for these attacks to converge to the aggregated models of the fair participants. We first show that a straightforward implementation of this attack can be simply achieved by not updating the local parameters during the iterative federated optimization. As this attack can be detected by adopting simple countermeasures at the server level, we subsequently study more complex disguising schemes based on stochastic updates of the free-rider parameters. We demonstrate the proposed strategies on a number of experimental scenarios, in both iid and non-iid settings. We conclude by providing recommendations to avoid free-rider attacks in real world applications of federated learning, especially in sensitive domains where security of data and models is critical.
APA
Fraboni, Y., Vidal, R. & Lorenzi, M.. (2021). Free-rider Attacks on Model Aggregation in Federated Learning . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:1846-1854 Available from https://proceedings.mlr.press/v130/fraboni21a.html.

Related Material