mlsanityData to 7 Oct 2026

MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks

arXiv 2207.07941 ↗First posted 16 Jul 2022cs.LG cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Implementations of SGD on distributed systems create new vulnerabilities, which can be identified and misused by one or more adversarial agents. Recently, it has been shown that well-known Byzantine-resilient gradient aggregation schemes are indeed vulnerable to informed attackers that can tailor the attacks (Fang et al., 2020; Xie et al., 2020b). We introduce MixTailor, a scheme based on randomization of the aggregation strategies that makes it impossible for the attacker to be fully informed. Deterministic schemes can be integrated into MixTailor on the fly without introducing any additional hyperparameters. Randomization decreases the capability of a powerful adversary to tailor its attacks, while the resulting randomized aggregation scheme is still competitive in terms of performance. For both iid and non-iid settings, we establish almost sure convergence guarantees that are both stronger and more general than those available in the literature. Our empirical studies across various datasets, attacks, and settings, validate our hypothesis and show that MixTailor successfully defends when well-known Byzantine-tolerant schemes fail.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 42 of its 70 references that are in the map. First posted on arXiv 16 Jul 2022.

Builds on

42 of 70 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  8. 2018How To Backdoor Federated Learningcited by 745
  9. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  10. 2020Federated Learning with Matched Averagingcited by 564
  11. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  12. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
30 more
  1. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  2. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  3. 2019Robust Aggregation for Federated Learningcited by 314
  4. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  5. 2019Error Feedback Fixes SignSGD and other Gradient Compression Schemescited by 306
  6. 2017Certified Defenses for Data Poisoning Attackscited by 288
  7. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  8. 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
  9. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 148
  10. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  11. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  12. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  13. 2016Agnostic Estimation of Mean and Covariancecited by 131
  14. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  15. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  16. 2018Byzantine Stochastic Gradient Descentcited by 81
  17. 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 74
  18. 2017Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descentcited by 59
  19. 2020Byzantine-Resilient Non-Convex Stochastic Gradient Descentcited by 56
  20. 2019Zeno++: Robust Fully Asynchronous SGDcited by 53
  21. 2019DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregationcited by 44
  22. 2020Adaptive Gradient Quantization for Data-Parallel SGDcited by 43
  23. 2017ByRDiE: Byzantine-resilient distributed coordinate descent for decentralized learningcited by 36
  24. 2021FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspectivecited by 35
  25. 2018Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learningcited by 32
  26. 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
  27. 2020Byzantine-Resilient High-Dimensional Federated Learningcited by 27
  28. 2019Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attackscited by 20
  29. 2019NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantizationcited by 17
  30. 2020Byzantine-Robust Decentralized Stochastic Optimization over Static and Time-Varying Networkscited by 10

Built on by

Cited by year

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

5 papers.

  1. 2023Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximizationcited by 1
  2. 2023Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learningcited by 1
  3. 2024Understanding Byzantine Robustness in Federated Learning with A Black-box Servercited by 1
  4. 2025Layer-wise Quantization for Quantized Optimistic Dual Averagingcited by 1
  5. 2023Loss- and Reward-Weighting for Efficient Distributed Reinforcement Learningcited by 0