BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning

• URL: http://arxiv.org/abs/2608.21137v2
• Date: Mon, 24 Aug 2026 06:30:33 GMT
• Title: BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
• Abstract summary: Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model exchange.<n>We argue that the robustness of DFL has been significantly overestimated.<n>We present BackDFL, a unified benchmark for systematically evaluating DFL under realistic and adaptive backdoor attacks.
• Score: 6.880692243968865
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model exchange. However, this architectural shift fundamentally reshapes the threat landscape. Without globally coordinated aggregation, DFL becomes particularly susceptible to backdoor attacks, in which malicious participants implant persistent hidden behaviors while maintaining high clean-task performance. In this paper, we argue that the robustness of DFL has been significantly overestimated. Existing studies rely on simplified threat models, non-adaptive adversaries, fragmented evaluation protocols, inconsistent communication topologies, and ad hoc training configurations, leading to an incomplete understanding of DFL security. To address these limitations, we present BackDFL, a unified benchmark for systematically evaluating DFL under realistic and adaptive backdoor attacks. Through extensive experiments, BackDFL exposes critical failure modes of decentralized learning. Our results demonstrate that both state-of-the-art Byzantine-robust DFL methods and adapted FL backdoor defenses fail under modest malicious participation rates (as low as 15%), especially in heterogeneous settings, while their robustness varies substantially across communication graph topologies.

Related papers

• On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy [12.421658400381082]
  We propose a novel and model poisoning attack framework tailored for LDPFL settings.<n>Our approach is driven by the objective of maximizing the global training loss while adhering to local privacy constraints.<n>We evaluate our framework across three representative LDPFL protocols, three benchmark datasets, and two types of deep neural networks.
  arXiv  Detail & Related papers  (2025-09-05T17:23:03Z)
• BDPFL: Backdoor Defense for Personalized Federated Learning via Explainable Distillation [30.400746330423605]
  Federated learning is a distributed learning paradigm that facilitates the collaborative training of a global model across multiple clients.<n>We propose a novel, backdoor-robust pFL framework named BDPFL to address these challenges.<n>First, BDPFL introduces layer-wise mutual distillation that enables clients to learn their personalized local models while mitigating potential backdoors.
  arXiv  Detail & Related papers  (2025-03-09T10:59:18Z)
• Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning [83.90283731845867]
  We consider feature reconstruction attacks, a common risk targeting input data compromise.<n>We show that Federated-based models are resistant to state-of-the-art feature reconstruction attacks.
  arXiv  Detail & Related papers  (2024-12-16T12:02:12Z)
• Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning [31.386836775526685]
  We propose textitPFedBA, a stealthy and effective backdoor attack strategy applicable to PFL systems. Our study sheds light on the subtle yet potent backdoor threats to PFL systems, urging the community to bolster defenses against emerging backdoor challenges.
  arXiv  Detail & Related papers  (2024-06-10T12:14:05Z)
• Sentinel: An Aggregation Function to Secure Decentralized Federated Learning [9.046402244232343]
  Decentralized Federated Learning (DFL) emerges as an innovative paradigm to train collaborative models, addressing the single point of failure limitation. Existing defense mechanisms have been designed for centralized FL and they do not adequately exploit the particularities of DFL. This work introduces Sentinel, a defense strategy to counteract poisoning attacks in DFL.
  arXiv  Detail & Related papers  (2023-10-12T07:45:18Z)
• Decentralized Federated Learning: A Survey and Perspective [45.81975053649379]
  Decentralized FL (DFL) is a decentralized network architecture that eliminates the need for a central server. DFL enables direct communication between clients, resulting in significant savings in communication resources.
  arXiv  Detail & Related papers  (2023-06-02T15:12:58Z)
• Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration [13.067285306737675]
  This paper investigates the vulnerability of vertical federated learning (VFL) in the context of binary classification tasks. We introduce a universal adversarial backdoor (UAB) attack to poison the predictions of VFL. Our approach surpasses existing state-of-the-art methods, achieving up to 100% backdoor task performance.
  arXiv  Detail & Related papers  (2023-04-22T15:31:15Z)
• BadVFL: Backdoor Attacks in Vertical Federated Learning [22.71527711053385]
  Federated learning (FL) enables multiple parties to collaboratively train a machine learning model without sharing their data. In this paper, we focus on robustness in VFL, in particular, on backdoor attacks. We present a first-of-its-kind clean-label backdoor attack in VFL, which consists of two phases: a label inference and a backdoor phase.
  arXiv  Detail & Related papers  (2023-04-18T09:22:32Z)
• Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks [53.81129518924231]
  We conduct the first study of backdoor attacks in the pFL framework. We show that pFL methods with partial model-sharing can significantly boost robustness against backdoor attacks. We propose a lightweight defense method, Simple-Tuning, which empirically improves defense performance against backdoor attacks.
  arXiv  Detail & Related papers  (2023-02-03T11:58:14Z)
• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning [66.56240101249803]
  We study how hardening benign clients can affect the global model (and the malicious clients) We propose a trigger reverse engineering based defense and show that our method can achieve improvement with guarantee robustness. Our results on eight competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks.
  arXiv  Detail & Related papers  (2022-10-23T22:24:03Z)
• Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks [68.20436971825941]
  Federated learning (FL) provides an efficient paradigm to jointly train a global model leveraging data from distributed users. Several studies have shown that FL is vulnerable to poisoning attacks. To protect the privacy of local users, FL is usually trained in a differentially private way.
  arXiv  Detail & Related papers  (2022-09-08T21:01:42Z)
• CRFL: Certifiably Robust Federated Learning against Backdoor Attacks [59.61565692464579]
  This paper provides the first general framework, Certifiably Robust Federated Learning (CRFL), to train certifiably robust FL models against backdoors. Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude.
  arXiv  Detail & Related papers  (2021-06-15T16:50:54Z)
• Meta Federated Learning [57.52103907134841]
  Federated Learning (FL) is vulnerable to training time adversarial attacks. We propose Meta Federated Learning ( Meta-FL) which not only is compatible with secure aggregation protocol but also facilitates defense against backdoor attacks.
  arXiv  Detail & Related papers  (2021-02-10T16:48:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.