DarkFed: A Data-Free Backdoor Attack in Federated Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Minghui, Wan, Wei, Ning, Yuxuan, Hu, Shengshan, Xue, Lulu, Zhang, Leo Yu, Wang, Yichen
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913342684135424
author Li, Minghui
Wan, Wei
Ning, Yuxuan
Hu, Shengshan
Xue, Lulu
Zhang, Leo Yu
Wang, Yichen
author_facet Li, Minghui
Wan, Wei
Ning, Yuxuan
Hu, Shengshan
Xue, Lulu
Zhang, Leo Yu
Wang, Yichen
contents Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development. To bridge this gap, we present DarkFed. Initially, we emulate a series of fake clients, thereby achieving the attacker proportion typical of academic research scenarios. Given that these emulated fake clients lack genuine training data, we further propose a data-free approach to backdoor FL. Specifically, we delve into the feasibility of injecting a backdoor using a shadow dataset. Our exploration reveals that impressive attack performance can be achieved, even when there is a substantial gap between the shadow dataset and the main task dataset. This holds true even when employing synthetic data devoid of any semantic information as the shadow dataset. Subsequently, we strategically construct a series of covert backdoor updates in an optimized manner, mimicking the properties of benign updates, to evade detection by defenses. A substantial body of empirical evidence validates the tangible effectiveness of DarkFed.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03299
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DarkFed: A Data-Free Backdoor Attack in Federated Learning
Li, Minghui
Wan, Wei
Ning, Yuxuan
Hu, Shengshan
Xue, Lulu
Zhang, Leo Yu
Wang, Yichen
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development. To bridge this gap, we present DarkFed. Initially, we emulate a series of fake clients, thereby achieving the attacker proportion typical of academic research scenarios. Given that these emulated fake clients lack genuine training data, we further propose a data-free approach to backdoor FL. Specifically, we delve into the feasibility of injecting a backdoor using a shadow dataset. Our exploration reveals that impressive attack performance can be achieved, even when there is a substantial gap between the shadow dataset and the main task dataset. This holds true even when employing synthetic data devoid of any semantic information as the shadow dataset. Subsequently, we strategically construct a series of covert backdoor updates in an optimized manner, mimicking the properties of benign updates, to evade detection by defenses. A substantial body of empirical evidence validates the tangible effectiveness of DarkFed.
title DarkFed: A Data-Free Backdoor Attack in Federated Learning
topic Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2405.03299