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

arXiv: https://arxiv.org/abs/2607.26933 · HTML: https://mlsanity.com/paper/2607.26933/

## 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 (most cited first, 26 of 26)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [Attack of the Tails: Yes, You Really Can Backdoor Federated Learning](https://mlsanity.com/paper/2007.05084/) (2020)
- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [Neurotoxin: Durable Backdoors in Federated Learning](https://mlsanity.com/paper/2206.10341/) (2022)
- [Multimodal Federated Learning via Contrastive Representation Ensemble](https://mlsanity.com/paper/2302.08888/) (2023)
- [Defending against Backdoors in Federated Learning with Robust Learning Rate](https://mlsanity.com/paper/2007.03767/) (2020)
- [Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity](https://mlsanity.com/paper/2302.01772/) (2023)
- [SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification](https://mlsanity.com/paper/2112.06274/) (2021)
- [Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees](https://mlsanity.com/paper/2002.10940/) (2020)
- [Relaxed Contrastive Learning for Federated Learning](https://mlsanity.com/paper/2401.04928/) (2024)
- [Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering](https://mlsanity.com/paper/2109.05872/) (2021)
- [Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity](https://mlsanity.com/paper/2309.13591/) (2023)
- [Multi-metrics adaptively identifies backdoors in Federated learning](https://mlsanity.com/paper/2303.06601/) (2023)
- [DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics](https://mlsanity.com/paper/2211.10878/) (2022)
- [Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection](https://mlsanity.com/paper/2503.07978/) (2025)
- [FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent](https://mlsanity.com/paper/2310.03156/) (2023)
- [Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2112.00407/) (2021)
- [Identify Backdoored Model in Federated Learning via Individual Unlearning](https://mlsanity.com/paper/2411.01040/) (2024)
- [Dual Class-Aware Contrastive Federated Semi-Supervised Learning](https://mlsanity.com/paper/2211.08914/) (2022)
- [PPFPL: Cross-silo Privacy-preserving Federated Prototype Learning Against Data Poisoning Attacks](https://mlsanity.com/paper/2504.03173/) (2025)

## 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.