mlsanityData to 14 Oct 2026

Towards Attack-tolerant Federated Learning via Critical Parameter Analysis

arXiv 2308.09318 ↗First posted 18 Aug 2023cs.LG cs.AI cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poisoning attacks when malicious clients send false updates to the central server. Existing defense strategies are ineffective under non-IID data settings. This paper proposes a new defense strategy, FedCPA (Federated learning with Critical Parameter Analysis). Our attack-tolerant aggregation method is based on the observation that benign local models have similar sets of top-k and bottom-k critical parameters, whereas poisoned local models do not. Experiments with different attack scenarios on multiple datasets demonstrate that our model outperforms existing defense strategies in defending against poisoning attacks.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

24 of 34 references.

References · 24

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  4. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  5. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  6. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  7. 2021Model-Contrastive Federated Learningcited by 766
  8. 2018How To Backdoor Federated Learningcited by 765
  9. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  10. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  11. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  12. 2018Spectral Signatures in Backdoor Attackscited by 484
12 more
  1. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  2. 2019Robust Aggregation for Federated Learningcited by 317
  3. 2021A Field Guide to Federated Optimizationcited by 315
  4. 2017Certified Defenses for Data Poisoning Attackscited by 303
  5. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  6. 2019Can You Really Backdoor Federated Learning?cited by 255
  7. 2020Threats to Federated Learning: A Surveycited by 178
  8. 2018Generalized Byzantine-tolerant SGDcited by 95
  9. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  10. 2022FedX: Unsupervised Federated Learning with Cross Knowledge Distillationcited by 40
  11. 2022FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation via Hard Samplingcited by 22
  12. 2023FedDefender: Client-Side Attack-Tolerant Federated Learningcited by 12

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 2.

7 papers.

  1. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 128
  2. 2024Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Modelscited by 18
  3. 2025Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Modelcited by 16
  4. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  5. 2024Poisoning with A Pill: Circumventing Detection in Federated Learningcited by 2
  6. 2025A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learningcited by 1
  7. 2024FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learningcited by 0