mlsanityData to 14 Oct 2026

Balancing Privacy, Robustness, and Efficiency in Machine Learning

arXiv 2312.14712 ↗First posted 22 Dec 2023cs.LG cs.CR cs.DCcited by 1

Not on the map. Why?

Abstract (arXiv)

This position paper argues that achieving robustness, privacy, and efficiency simultaneously in machine learning systems is infeasible under prevailing threat models. The tension between these goals arises not from algorithmic shortcomings but from structural limitations imposed by worst-case adversarial assumptions. We advocate for a systematic research agenda aimed at formalizing the robustness-privacy-efficiency trilemma, exploring how principled relaxations of threat models can unlock better trade-offs, and designing benchmarks that expose rather than obscure the compromises made. By shifting focus from aspirational universal guarantees to context-aware system design, the machine learning community can build models that are truly appropriate for real-world deployment.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 46 of its 77 references that are in the map. First posted on arXiv 22 Dec 2023.

Builds on

46 of 77 references.

References · 46

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  7. 2018How To Backdoor Federated Learningcited by 765
  8. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  9. 2020The Future of Digital Health with Federated Learningcited by 633
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  11. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 346
  12. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
34 more
  1. 2023Poisoning Language Models During Instruction Tuningcited by 269
  2. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  3. 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
  4. 2019MLPerf Inference Benchmarkcited by 199
  5. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
  6. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  7. 2016Distributed Mean Estimation with Limited Communicationcited by 136
  8. 2016Agnostic Estimation of Mean and Covariancecited by 131
  9. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  10. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
  11. 2023Universal Jailbreak Backdoors from Poisoned Human Feedbackcited by 128
  12. 2018Sever: A Robust Meta-Algorithm for Stochastic Optimizationcited by 125
  13. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
  14. 2018Distributed Differential Privacy via Shufflingcited by 115
  15. 2019Data Poisoning against Differentially-Private Learners: Attacks and Defensescited by 78
  16. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 78
  17. 2020Breaking the Communication-Privacy-Accuracy Trilemmacited by 68
  18. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 65
  19. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  20. 2020Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)cited by 54
  21. 2019Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detectioncited by 41
  22. 2016Geometric Median in Nearly Linear Timecited by 39
  23. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 36
  24. 2019Manipulation Attacks in Local Differential Privacycited by 28
  25. 2022On the Impossible Safety of Large AI Modelscited by 28
  26. 2023From Robustness to Privacy and Backcited by 27
  27. 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
  28. 2020An Accurate, Scalable and Verifiable Protocol for Federated Differentially Private Averagingcited by 20
  29. 2020Secure Byzantine-Robust Machine Learningcited by 19
  30. 2021Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?cited by 18
  31. 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attackscited by 12
  32. 2022Suppressing Poisoning Attacks on Federated Learning for Medical Imagingcited by 8
  33. 2021Robust Testing and Estimation under Manipulation Attackscited by 5
  34. 2022Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Predictioncited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Adaptive Gradient Clipping for Robust Federated Learningcited by 11