mlsanityData to 7 Oct 2026

Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling

arXiv 2204.14017 ↗First posted 29 Apr 2022cs.LG cs.AI cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the framework to poison the global model for an adversarial purpose. This paper investigates the feasibility of model poisoning for backdoor attacks through rare word embeddings of NLP models. In text classification, less than 1% of adversary clients suffices to manipulate the model output without any drop in the performance on clean sentences. For a less complex dataset, a mere 0.1% of adversary clients is enough to poison the global model effectively. We also propose a technique specialized in the federated learning scheme called Gradient Ensemble, which enhances the backdoor performance in all our experimental settings.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

21 of 37 references.

References · 21

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  4. 2016Pointer Sentinel Mixture Modelscited by 2,992
  5. 2020Adaptive Federated Optimizationcited by 1,036
  6. 2019Towards Federated Learning at Scale: System Designcited by 826
  7. 2018How To Backdoor Federated Learningcited by 745
  8. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  9. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  10. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  12. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 318
9 more
  1. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  2. 2018FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Mediacited by 281
  3. 2019Can You Really Backdoor Federated Learning?cited by 250
  4. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  5. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  6. 2021Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Modelscited by 96
  7. 2020Subpopulation Data Poisoning Attackscited by 68
  8. 2021Stronger Privacy for Federated Collaborative Filtering with Implicit Feedbackcited by 26
  9. 2019Federated and Differentially Private Learning for Electronic Health Recordscited by 13

Built on by

Cited by year

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

8 papers.

  1. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  2. 2023Grounding Foundation Models through Federated Transfer Learning: A General Frameworkcited by 24
  3. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  4. 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregationcited by 8
  5. 2022Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-Endcited by 6
  6. 2024R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Modelscited by 5
  7. 2025NLP Security and Ethics, in the Wildcited by 2
  8. 2025On the Out-of-Distribution Backdoor Attack for Federated Learningcited by 1