mlsanityData to 14 Oct 2026

Peak-Controlled Logits Poisoning Attack in Federated Distillation

arXiv 2407.18039 ↗First posted 25 Jul 2024cs.LG cs.AIcited by 1

On the map: Knowledge distillation → Federated, robust and private distillation

Abstract (arXiv)

Federated Distillation (FD) offers an innovative approach to distributed machine learning, leveraging knowledge distillation for efficient and flexible cross-device knowledge transfer without necessitating the upload of extensive model parameters to a central server. While FD has gained popularity, its vulnerability to poisoning attacks remains underexplored. To address this gap, we previously introduced FDLA (Federated Distillation Logits Attack), a method that manipulates logits communication to mislead and degrade the performance of client models. However, the impact of FDLA on participants with different identities and the effects of malicious modifications at various stages of knowledge transfer remain unexplored. To this end, we present PCFDLA (Peak-Controlled Federated Distillation Logits Attack), an advanced and more stealthy logits poisoning attack method for FD. PCFDLA enhances the effectiveness of FDLA by carefully controlling the peak values of logits to create highly misleading yet inconspicuous modifications. Furthermore, we introduce a novel metric for better evaluating attack efficacy, demonstrating that PCFDLA maintains stealth while being significantly more disruptive to victim models compared to its predecessors. Experimental results across various datasets confirm the superior impact of PCFDLA on model accuracy, solidifying its potential threat in federated distillation systems.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation. Builds on 29 of its 48 references that are in the map. First posted on arXiv 25 Jul 2024.

Builds on

29 of 48 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Logits Poisoning Attack in Federated Distillation8 Jan
  2. 2024Federated Class-Incremental Learning with New-Class Augmented Self-Distillation1 Jan
  3. 2023FedICT: Federated Multi-task Distillation for Multi-access Edge Computing1 Jan
  4. 2022Knowledge Distillation for Federated Learning: a Practical Guide9 Nov
  5. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillation30 Aug

Other references · 24

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2018Federated Learning with Non-IID Datacited by 1,108
  6. 2021Towards Personalized Federated Learningcited by 464
  7. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  8. 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 316
  9. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 243
  10. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  11. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 109
  12. 2022Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learningcited by 81
12 more
  1. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
  2. 2020Data Poisoning Attacks on Federated Machine Learningcited by 62
  3. 2022Communication-Efficient Adaptive Federated Learningcited by 55
  4. 2021FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusioncited by 49
  5. 2022Federated Unlearning for On-Device Recommendationcited by 43
  6. 2020Federated Edge Learning : Design Issues and Challengescited by 26
  7. 2022Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillationcited by 22
  8. 2023FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligencecited by 17
  9. 2024Federated Distillation: A Surveycited by 15
  10. 2023Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaborationcited by 10
  11. 2021Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfercited by 7
  12. 2024Poisoning Attacks and Defenses in Recommender Systems: A Surveycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SCENE OTA-FD: Self-Centering Noncoherent Estimator for Over-the-Air Federated Distillationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Logit Poisoning Attack in Distillation-based Federated Learning and its Countermeasures ↗
  2. 2025DROP: Poison Dilution via Knowledge Distillation for Federated Learning
  3. 2025SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  4. 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning
  5. 2024Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning
  6. 2025Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks
  7. 2025Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
  8. 2024HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning