mlsanityData to 14 Oct 2026

Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning

arXiv 2607.26933 ↗First posted 29 Jul 2026cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is vulnerable to backdoor attacks because of its distributed nature in edge computing scenarios. Existing defense methods show limited efficacy as they overlook the deviations among benign local updates caused by statistical heterogeneity and the stealthiness of backdoor attacks. To tackle these issues, we propose FedDAB, a two-phase method that combines local contrastive regularization with alignment checking, to defend against backdoor attacks. In the first phase, FedDAB introduces a novel model-contrastive term into the local objective to enhance direction and magnitude consistency among benign updates. In the second phase, FedDAB employs an alignment checking strategy to evaluate each local update in terms of overall-direction alignment and parameter-level alignment with historical information, excluding updates that exhibit abnormal alignment patterns from global aggregation. We theoretically prove FedDAB's robustness with a convergence rate of O(1/T). Extensive experiments show that FedDAB outperforms existing defense methods against backdoor attacks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 47 references that are in the map. First posted on arXiv 29 Jul 2026.

Builds on

26 of 47 references.

References · 26

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  6. 2021Model-Contrastive Federated Learningcited by 766
  7. 2019Robust Aggregation for Federated Learningcited by 317
  8. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  9. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  10. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
  11. 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 86
  12. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
14 more
  1. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 65
  2. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  3. 2020Stochastic-Sign SGD for Federated Learning with Theoretical Guaranteescited by 35
  4. 2024Relaxed Contrastive Learning for Federated Learningcited by 32
  5. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 30
  6. 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 26
  7. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  8. 2022DYNAFED: Tackling Client Data Heterogeneity with Global Dynamicscited by 22
  9. 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspectioncited by 13
  10. 2023FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descentcited by 8
  11. 2021Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Datacited by 4
  12. 2024Identify Backdoored Model in Federated Learning via Individual Unlearningcited by 4
  13. 2022Dual Class-Aware Contrastive Federated Semi-Supervised Learningcited by 3
  14. 2025PPFPL: Cross-silo Privacy-preserving Federated Prototype Learning Against Data Poisoning Attackscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
  2. 2026FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
  3. 2024Client-Side Patching against Backdoor Attacks in Federated Learning
  4. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
  5. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
  6. 2025TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
  7. 2022Invariant Aggregator for Defending against Federated Backdoor Attacks
  8. 2022Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection