mlsanityData to 14 Oct 2026

Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning

arXiv 2412.07454 ↗First posted 10 Dec 2024cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated learning enables decentralized model training without sharing raw data, preserving data privacy. However, its vulnerability towards critical security threats, such as gradient inversion and model poisoning by malicious clients, remain unresolved. Existing solutions often address these issues separately, sacrificing either system robustness or model accuracy. This work introduces Tazza, a secure and efficient federated learning framework that simultaneously addresses both challenges. By leveraging the permutation equivariance and invariance properties of neural networks via weight shuffling and shuffled model validation, Tazza enhances resilience against diverse poisoning attacks, while ensuring data confidentiality and high model accuracy. Comprehensive evaluations on various datasets and embedded platforms show that Tazza achieves robust defense with up to 6.7x improved computational efficiency compared to alternative schemes, without compromising performance.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 75 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

34 of 75 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  5. 2016Deep Learning with Differential Privacycited by 2,728
  6. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  7. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  8. 2019Deep Leakage from Gradientscited by 1,021
  9. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  10. 2018How To Backdoor Federated Learningcited by 765
  11. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  12. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
22 more
  1. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  2. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  3. 2021Intriguing Properties of Vision Transformerscited by 446
  4. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  5. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  6. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
  7. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  8. 2018Generalized Byzantine-tolerant SGDcited by 95
  9. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  10. 2022NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Bettercited by 43
  11. 2017Parallel Multi Channel Convolution using General Matrix Multiplicationcited by 30
  12. 2021JigsawGAN: Auxiliary Learning for Solving Jigsaw Puzzles with Generative Adversarial Networkscited by 16
  13. 2021Differential Privacy in the Shuffle Model: A Survey of Separationscited by 15
  14. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
  15. 2023ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer's Diseasecited by 14
  16. 2024Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generationcited by 9
  17. 2023FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Thingscited by 8
  18. 2024DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learningcited by 5
  19. 2022Fast Monte-Carlo Approximation of the Attention Mechanismcited by 3
  20. 2022FedPerm: Private and Robust Federated Learning by Parameter Permutationcited by 3
  21. 2019Compiler-Level Matrix Multiplication Optimization for Deep Learningcited by 1
  22. 2024ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classificationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Temperature Scaling Attack Disrupting Model Confidence in Federated Learningcited by 0
  2. 2026MPT: Missing Prototype Tracking via Barycentric Reconstruction in Vehicular Federated Learningcited by 0