# Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection

arXiv: https://arxiv.org/abs/2503.07978 · HTML: https://mlsanity.com/paper/2503.07978/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 58 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [Why gradient clipping accelerates training: A theoretical justification for adaptivity](https://mlsanity.com/paper/1905.11881/) (2019)
- [The Hidden Vulnerability of Distributed Learning in Byzantium](https://mlsanity.com/paper/1802.07927/) (2018)
- [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)
- [A Little Is Enough: Circumventing Defenses For Distributed Learning](https://mlsanity.com/paper/1902.06156/) (2019)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [Federated Learning for Open Banking](https://mlsanity.com/paper/2108.10749/) (2021)
- [Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing](https://mlsanity.com/paper/2006.09365/) (2020)
- [Neurotoxin: Durable Backdoors in Federated Learning](https://mlsanity.com/paper/2206.10341/) (2022)
- [Defending against Backdoors in Federated Learning with Robust Learning Rate](https://mlsanity.com/paper/2007.03767/) (2020)
- [DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection](https://mlsanity.com/paper/2201.00763/) (2022)
- [Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity](https://mlsanity.com/paper/2302.01772/) (2023)
- [Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums](https://mlsanity.com/paper/2205.12173/) (2022)
- [Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)](https://mlsanity.com/paper/2008.00742/) (2020)
- [SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification](https://mlsanity.com/paper/2112.06274/) (2021)
- [Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy](https://mlsanity.com/paper/2202.07178/) (2022)
- [Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning](https://mlsanity.com/paper/2207.04338/) (2022)
- [Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering](https://mlsanity.com/paper/2109.05872/) (2021)
- [CrowdGuard: Federated Backdoor Detection in Federated Learning](https://mlsanity.com/paper/2210.07714/) (2022)
- [On the Vulnerability of Backdoor Defenses for Federated Learning](https://mlsanity.com/paper/2301.08170/) (2023)
- [Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms](https://mlsanity.com/paper/2007.12004/) (2020)
- [Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity](https://mlsanity.com/paper/2309.13591/) (2023)

## Built on by (most cited first, 13 of 13)

- [Traceable Black-box Watermarks for Federated Learning](https://mlsanity.com/paper/2505.13651/) (2025)
- [Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning](https://mlsanity.com/paper/2505.10297/) (2025)
- [Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy](https://mlsanity.com/paper/2505.13655/) (2025)
- [BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning](https://mlsanity.com/paper/2507.04903/) (2025)
- [Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs](https://mlsanity.com/paper/2508.20333/) (2025)
- [On the Out-of-Distribution Backdoor Attack for Federated Learning](https://mlsanity.com/paper/2509.13219/) (2025)
- [FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement](https://mlsanity.com/paper/2605.11122/) (2026)
- [Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning](https://mlsanity.com/paper/2605.19969/) (2026)
- [FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning](https://mlsanity.com/paper/2508.04064/) (2025)
- [Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning](https://mlsanity.com/paper/2607.26933/) (2026)
- [FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devices](https://mlsanity.com/paper/2608.01095/) (2026)
- [Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning](https://mlsanity.com/paper/2609.27760/) (2026)
- [Backdoor Mitigation in Decentralized LLM Fine-Tuning](https://mlsanity.com/paper/2609.37367/) (2026)

## Abstract (arXiv)

The distributed nature of training makes Federated Learning (FL) vulnerable to backdoor attacks, where malicious model updates aim to compromise the global model's performance on specific tasks. Existing defense methods show limited efficacy as they overlook the inconsistency between benign and malicious model updates regarding both general and fine-grained directions. To fill this gap, we introduce AlignIns, a novel defense method designed to safeguard FL systems against backdoor attacks. AlignIns looks into the direction of each model update through a direction alignment inspection process. Specifically, it examines the alignment of model updates with the overall update direction and analyzes the distribution of the signs of their significant parameters, comparing them with the principle sign across all model updates. Model updates that exhibit an unusual degree of alignment are considered malicious and thus be filtered out. We provide the theoretical analysis of the robustness of AlignIns and its propagation error in FL. Our empirical results on both independent and identically distributed (IID) and non-IID datasets demonstrate that AlignIns achieves higher robustness compared to the state-of-the-art defense methods. The code is available at https://github.com/JiiahaoXU/AlignIns.