mlsanityData to 14 Oct 2026

DCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personal Federated Learning

arXiv 2602.18489 ↗First posted 11 Feb 2026cs.CR cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized federated learning (PFL) creates client-specific models to handle data heterogeneity. Previously, PFL has been shown to be naturally resistant to backdoor attack propagation across clients. In this work, we reveal that PFL remains vulnerable to backdoor attacks through a novel frequency-domain approach. We propose DCInject, an adaptive frequency-domain backdoor attack for PFL, which removes portions of the zero-frequency (DC) component and replaces them with Gaussian-distributed samples in the frequency domain. Our attack achieves superior attack success rates while maintaining clean accuracy across four datasets (CIFAR-10/100, GTSRB, SVHN) compared to existing spatial-domain attacks, evaluated under parameter decoupling based personalization. DCInject achieves superior performance with ASRs of 96.83% (CIFAR-10), 99.38% (SVHN), and 100% (GTSRB) while maintaining clean accuracy. Under I-BAU defense, DCInject demonstrates strong persistence, retaining 90.30% ASR vs BadNet's 58.56% on VGG-16, exposing critical vulnerabilities in PFL security assumptions. Our code is available at https://github.com/NahomMA/DCINject-PFL

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

15 of 21 references.

References · 15

  1. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  2. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  3. 2018Federated Learning with Non-IID Datacited by 1,108
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  6. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  7. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  8. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  9. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  10. 2021Adversarial Unlearning of Backdoors via Implicit Hypergradientcited by 166
  11. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  12. 2023Revisiting Personalized Federated Learning: Robustness Against Backdoor Attackscited by 16
3 more
  1. 2024Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learningcited by 6
  2. 2023FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learningcited by 5
  3. 2025Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025BDPFL: Backdoor Defense for Personalized Federated Learning via Explainable Distillation
  2. 2025FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
  3. 2022PerDoor: Persistent Non-Uniform Backdoors in Federated Learning using Adversarial Perturbations
  4. 2025SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning
  5. 2023You Can Backdoor Personalized Federated Learning
  6. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
  7. 2024DarkFed: A Data-Free Backdoor Attack in Federated Learning
  8. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning