Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) is a popular paradigm enabling clients to jointly train a global model without sharing raw data. However, FL is known to be vulnerable towards backdoor attacks due to its distributed nature. As participants, attackers can upload model updates that effectively compromise FL. What's worse, existing defenses are mostly designed under independent-and-identically-distributed (iid) settings, hence neglecting the fundamental non-iid characteristic of FL. Here we propose FLBuff for tackling backdoor attacks even under non-iids. The main challenge for such defenses is that non-iids bring benign and malicious updates closer, hence harder to separate. FLBuff is inspired by our insight that non-iids can be modeled as omni-directional expansion in representation space while backdoor attacks as uni-directional. This leads to the key design of FLBuff, i.e., a supervised-contrastive-learning model extracting penultimate-layer representations to create a large in-between buffer layer. Comprehensive evaluations demonstrate that FLBuff consistently outperforms state-of-the-art defenses.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 30 Mar 2025.
Builds on
19 of 30 references.
References · 19
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
- 2020What Makes for Good Views for Contrastive Learning?cited by 846
- 2018How To Backdoor Federated Learningcited by 765
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
- 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
- 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
- 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
- 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
- 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
7 more
- 2022CrowdGuard: Federated Backdoor Detection in Federated Learningcited by 27
- 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learningcited by 27
- 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 21
- 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
- 2024Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learningcited by 5
- 2024BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learningcited by 3
- 2024FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Modelscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Mitigating Backdoors in Federated Learning with FLD
- 2023On the Vulnerability of Backdoor Defenses for Federated Learning
- 2025FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRning
- 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning
- 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
- 2023BayBFed: Bayesian Backdoor Defense for Federated Learning
- 2024Securing Federated Learning against Backdoor Threats with Foundation Model Integration
- 2022Towards a Defense Against Federated Backdoor Attacks Under Continuous Training