mlsanityData to 7 Oct 2026

Enhanced Security and Privacy via Fragmented Federated Learning

arXiv 2207.05978 ↗First posted 13 Jul 2022cs.CR cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In federated learning (FL), a set of participants share updates computed on their local data with an aggregator server that combines updates into a global model. However, reconciling accuracy with privacy and security is a challenge to FL. On the one hand, good updates sent by honest participants may reveal their private local information, whereas poisoned updates sent by malicious participants may compromise the model's availability and/or integrity. On the other hand, enhancing privacy via update distortion damages accuracy, whereas doing so via update aggregation damages security because it does not allow the server to filter out individual poisoned updates. To tackle the accuracy-privacy-security conflict, we propose em fragmented federated learning (FFL), in which participants randomly exchange and mix fragments of their updates before sending them to the server. To achieve privacy, we design a lightweight protocol that allows participants to privately exchange and mix encrypted fragments of their updates so that the server can neither obtain individual updates nor link them to their originators. To achieve security, we design a reputation-based defense tailored for FFL that builds trust in participants and their mixed updates based on the quality of the fragments they exchange and the mixed updates they send. Since the exchanged fragments' parameters keep their original coordinates and attackers can be neutralized, the server can correctly reconstruct a global model from the received mixed updates without accuracy loss. Experiments on four real data sets show that FFL can prevent semi-honest servers from mounting privacy attacks, can effectively counter poisoning attacks and can keep the accuracy of the global model.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 35 of its 74 references that are in the map. First posted on arXiv 13 Jul 2022.

Builds on

35 of 74 references.

References · 35

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2019Deep Leakage from Gradientscited by 1,004
  6. 2019Towards Federated Learning at Scale: System Designcited by 826
  7. 2018How To Backdoor Federated Learningcited by 745
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  9. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  11. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  12. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
23 more
  1. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  2. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  3. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  4. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  5. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  6. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  7. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  8. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
  9. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
  10. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  11. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 148
  12. 2016End-to-end Learning of Driving Models from Large-scale Video Datasetscited by 147
  13. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  14. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  15. 2019Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfercited by 91
  16. 2019Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attackscited by 79
  17. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  18. 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 74
  19. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  20. 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learningcited by 27
  21. 2020Achieving Security and Privacy in Federated Learning Systems: Survey, Research Challenges and Future Directionscited by 25
  22. 2020The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning)cited by 22
  23. 2021Secure and Privacy-Preserving Federated Learning via Co-Utilitycited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortioncited by 6
  2. 2023FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Userscited by 3
  3. 2025AI-driven Personalized Privacy Assistants: a Systematic Literature Reviewcited by 0