mlsanityData to 7 Oct 2026

RoFL: Robustness of Secure Federated Learning

arXiv 2107.03311 ↗First posted 7 Jul 2021cs.CR cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we demystify the inner workings of existing (targeted) attacks. We provide new insights into why these attacks are possible and why a definitive solution to FL robustness is challenging. We show that the need for ML algorithms to memorize tail data has significant implications for FL integrity. This phenomenon has largely been studied in the context of privacy; our analysis sheds light on its implications for ML integrity. We show that certain classes of severe attacks can be mitigated effectively by enforcing constraints such as norm bounds on clients' updates. We investigate how to efficiently incorporate these constraints into secure FL protocols in the single-server setting. Based on this, we propose RoFL, a new secure FL system that extends secure aggregation with privacy-preserving input validation. Specifically, RoFL can enforce constraints such as L2 and L_∞ bounds on high-dimensional encrypted model updates.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 41 of its 109 references that are in the map. First posted on arXiv 7 Jul 2021.

Builds on

41 of 109 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2020Extracting Training Data from Large Language Modelscited by 2,144
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  7. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  10. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  11. 2018LEAF: A Benchmark for Federated Settingscited by 780
  12. 2018How To Backdoor Federated Learningcited by 745
29 more
  1. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  3. 2020The Future of Digital Health with Federated Learningcited by 625
  4. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  5. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  6. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 452
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  8. 2018Measuring the Intrinsic Dimension of Objective Landscapescited by 364
  9. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  10. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  11. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  12. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  13. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  14. 2019Can You Really Backdoor Federated Learning?cited by 250
  15. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  16. 2018Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentationcited by 148
  17. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  18. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  19. 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 115
  20. 2017The Devil is in the Tails: Fine-grained Classification in the Wildcited by 89
  21. 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 74
  22. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  23. 2018Model-Reuse Attacks on Deep Learning Systemscited by 47
  24. 2019DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregationcited by 44
  25. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 35
  26. 2020Lightweight Techniques for Private Heavy Hitterscited by 13
  27. 2015Efficient Private Statistics with Succinct Sketchescited by 10
  28. 2018Differentially-Private "Draw and Discard" Machine Learningcited by 7
  29. 2018TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Controlcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 6; 2026: 6.

23 papers.

Sort:

By area:

  1. 2023Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Surveycited by 18
  2. 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 16
  3. 2024RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregationcited by 10
  4. 2025TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learningcited by 4
  5. 2024UTrace: Poisoning Forensics for Private Collaborative Learningcited by 3
  6. 2023FLIPS: Federated Learning using Intelligent Participant Selectioncited by 2
  7. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  8. 2023AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learningcited by 1
  9. 2024On the Conflict of Robustness and Learning in Collaborative Machine Learningcited by 1
  10. 2024Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defensecited by 1
  11. 2024Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attackscited by 1
  12. 2024Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocolscited by 1
11 more
  1. 2025FuSeFL: Fully Secure and Scalable Federated Learningcited by 1
  2. 2026ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learningcited by 1
  3. 2024Fluent: Round-efficient Secure Aggregation for Private Federated Learningcited by 0
  4. 2025SLVR: Securely Leveraging Client Validation for Robust Federated Learningcited by 0
  5. 2025Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learningcited by 0
  6. 2025Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learningcited by 0
  7. 2026FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clientscited by 0
  8. 2026Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversariescited by 0
  9. 2026Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregationcited by 0
  10. 2026Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructurecited by 0
  11. 2026OPFL: Optimistic Verification of Federated Learning via Empirical Boundarycited by 0