Leveraging MTD to Mitigate Poisoning Attacks in Decentralized FL with Non-IID Data
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917834261528576 |
|---|---|
| author | Feng, Chao Celdrán, Alberto Huertas Zeng, Zien Ye, Zi von der Assen, Jan Bovet, Gerome Stiller, Burkhard |
| author_facet | Feng, Chao Celdrán, Alberto Huertas Zeng, Zien Ye, Zi von der Assen, Jan Bovet, Gerome Stiller, Burkhard |
| contents | Decentralized Federated Learning (DFL), a paradigm for managing big data in a privacy-preserved manner, is still vulnerable to poisoning attacks where malicious clients tamper with data or models. Current defense methods often assume Independently and Identically Distributed (IID) data, which is unrealistic in real-world applications. In non-IID contexts, existing defensive strategies face challenges in distinguishing between models that have been compromised and those that have been trained on heterogeneous data distributions, leading to diminished efficacy. In response, this paper proposes a framework that employs the Moving Target Defense (MTD) approach to bolster the robustness of DFL models. By continuously modifying the attack surface of the DFL system, this framework aims to mitigate poisoning attacks effectively. The proposed MTD framework includes both proactive and reactive modes, utilizing a reputation system that combines metrics of model similarity and loss, alongside various defensive techniques. Comprehensive experimental evaluations indicate that the MTD-based mechanism significantly mitigates a range of poisoning attack types across multiple datasets with different topologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19302 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging MTD to Mitigate Poisoning Attacks in Decentralized FL with Non-IID Data Feng, Chao Celdrán, Alberto Huertas Zeng, Zien Ye, Zi von der Assen, Jan Bovet, Gerome Stiller, Burkhard Cryptography and Security Distributed, Parallel, and Cluster Computing Decentralized Federated Learning (DFL), a paradigm for managing big data in a privacy-preserved manner, is still vulnerable to poisoning attacks where malicious clients tamper with data or models. Current defense methods often assume Independently and Identically Distributed (IID) data, which is unrealistic in real-world applications. In non-IID contexts, existing defensive strategies face challenges in distinguishing between models that have been compromised and those that have been trained on heterogeneous data distributions, leading to diminished efficacy. In response, this paper proposes a framework that employs the Moving Target Defense (MTD) approach to bolster the robustness of DFL models. By continuously modifying the attack surface of the DFL system, this framework aims to mitigate poisoning attacks effectively. The proposed MTD framework includes both proactive and reactive modes, utilizing a reputation system that combines metrics of model similarity and loss, alongside various defensive techniques. Comprehensive experimental evaluations indicate that the MTD-based mechanism significantly mitigates a range of poisoning attack types across multiple datasets with different topologies. |
| title | Leveraging MTD to Mitigate Poisoning Attacks in Decentralized FL with Non-IID Data |
| topic | Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2409.19302 |