mlsanityData to 7 Oct 2026

PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local Examples

arXiv 2403.06131 ↗First posted 10 Mar 2024cs.CR cs.AIcited by 3

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Instruction tuning aligns large language models (LLMs) with human intentions but requires diverse, high-quality data that are difficult to collect in privacy-sensitive domains. Federated instruction tuning (FedIT) enables collaborative training across data owners, yet existing methods typically assume sufficient local data. In realistic few-shot settings, limited samples can cause overfitting, degrade performance, and increase vulnerability to training data extraction attacks. We propose PPFedIT, a federated algorithm that improves both model performance and privacy protection in federated few-shot learning. It comprises three client-side steps: (1) synthetic data generation, which uses LLMs to diversify and enrich local data; (2) parameter isolation training, which updates the shared global LLM on synthetic data and local LLMs on private local data to mitigate synthetic-data noise; and (3) local aggregation then sharing, which mixes global and local model parameters before uploading them for server aggregation to mitigate data extraction attacks. Experiments on three open-source datasets show that PPFedIT improves model performance by an average of 8.4% and reduces the risk of data extraction attacks by approximately 20% in challenging federated few-shot settings.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 38 of its 55 references that are in the map. First posted on arXiv 10 Mar 2024.

Builds on

38 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning25 Aug

Other references · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2020Longformer: The Long-Document Transformercited by 3,362
  8. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  9. 2016Deep Learning with Differential Privacycited by 2,682
  10. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  11. 2020Extracting Training Data from Large Language Modelscited by 2,144
  12. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
25 more
  1. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  2. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  3. 2020Adaptive Federated Optimizationcited by 1,036
  4. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  5. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  6. 2024TinyLlama: An Open-Source Small Language Modelcited by 604
  7. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  8. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  9. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 301
  10. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  11. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 194
  12. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 146
  13. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 124
  14. 2023MoDS: Model-oriented Data Selection for Instruction Tuningcited by 107
  15. 2023AlpaCare:Instruction-tuned Large Language Models for Medical Applicationcited by 88
  16. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 84
  17. 2022Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Modelscited by 52
  18. 2020TextHide: Tackling Data Privacy in Language Understanding Taskscited by 32
  19. 2024Genie: Achieving Human Parity in Content-Grounded Datasets Generationcited by 31
  20. 2023Federated Learning-Empowered AI-Generated Content in Wireless Networkscited by 26
  21. 2022Federated Few-Shot Learning for Mobile NLPcited by 15
  22. 2023A Split-and-Privatize Framework for Large Language Model Fine-Tuningcited by 11
  23. 2022Towards Practical Few-shot Federated NLPcited by 5
  24. 2022FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Taskscited by 3
  25. 2023Federated Learning Empowered by Generative Contentcited by 3

Built on by

Cited by year

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

3 papers.

  1. 2024Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Modelscited by 18
  2. 2025Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directionscited by 10
  3. 2024Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Modelscited by 2