mlsanityData to 7 Oct 2026

Robust Federated Learning with Attack-Adaptive Aggregation

arXiv 2102.05257 ↗First posted 10 Feb 2021cs.LG cs.CRcited by 17

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. To address this challenge, we propose an attack-adaptive aggregation strategy to defend against various attacks for robust federated learning. The proposed approach is based on training a neural network with an attention mechanism that learns the vulnerability of federated learning models from a set of plausible attacks. To the best of our knowledge, our aggregation strategy is the first one that can be adapted to defend against various attacks in a data-driven fashion. Our approach has achieved competitive performance in defending model poisoning and backdoor attacks in federated learning tasks on image and text datasets.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 38 of its 54 references that are in the map. First posted on arXiv 10 Feb 2021.

Builds on

38 of 54 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  8. 2016Deep Learning with Differential Privacycited by 2,682
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  11. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  12. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
26 more
  1. 2018How To Backdoor Federated Learningcited by 745
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  3. 2017Federated Multi-Task Learningcited by 669
  4. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  5. 2020Federated Learning with Matched Averagingcited by 564
  6. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  7. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  8. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  9. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  10. 2019Robust Aggregation for Federated Learningcited by 314
  11. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  12. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  13. 2019Can You Really Backdoor Federated Learning?cited by 250
  14. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
  15. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  16. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  17. 2018Sever: A Robust Meta-Algorithm for Stochastic Optimizationcited by 123
  18. 2020Distilled One-Shot Federated Learningcited by 108
  19. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 86
  20. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  21. 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 66
  22. 2019DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregationcited by 44
  23. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  24. 2019Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithmscited by 29
  25. 2018Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerancecited by 8
  26. 2018A probabilistic framework for multi-view feature learning with many-to-many associations via neural networkscited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 7; 2023: 3; 2024: 4; 2025: 2.

17 papers.

Sort:

By area:

  1. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  2. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  3. 2021Federated Learning Meets Natural Language Processing: A Surveycited by 42
  4. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  5. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  6. 2022Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspectivecited by 8
  7. 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregationcited by 8
  8. 2022Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learningcited by 7
  9. 2022Robust Federated Learning against both Data Heterogeneity and Poisoning Attack via Aggregation Optimizationcited by 3
  10. 2024Fin-Fed-OD: Federated Outlier Detection on Financial Tabular Datacited by 3
  11. 2022Towards Understanding Quality Challenges of the Federated Learning for Neural Networks: A First Look from the Lens of Robustnesscited by 1
  12. 2024Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labelscited by 1
5 more
  1. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learningcited by 1
  2. 2022Federated Adversarial Training with Transformerscited by 0
  3. 2024Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learningcited by 0
  4. 2024A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learningcited by 0
  5. 2025FedStrategist: A Meta-Learning Framework for Adaptive and Robust Aggregation in Federated Learningcited by 0