Buchumschlag

LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wu, Huiyu, Klabjan, Diego
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness
von: Salehi, Hojat Allah, et al.
Veröffentlicht: (2024)

Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning
von: Liu, Xiao-Yang, et al.
Veröffentlicht: (2023)

Robust softmax aggregation on blockchain based federated learning with convergence guarantee
von: Wu, Huiyu, et al.
Veröffentlicht: (2023)

ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy
von: Kato, Fumiyuki, et al.
Veröffentlicht: (2023)

Private and Communication-Efficient Federated Learning based on Differentially Private Sketches
von: Zhang, Meifan, et al.
Veröffentlicht: (2024)

Differentially Private Subspace Fine-Tuning for Large Language Models
von: Zheng, Lele, et al.
Veröffentlicht: (2026)

Differentially Private Federated Learning: A Systematic Review
von: Fu, Jie, et al.
Veröffentlicht: (2024)

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
von: Sha, Haichao, et al.
Veröffentlicht: (2026)

PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning
von: Gong, Chen, et al.
Veröffentlicht: (2025)

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
von: Jin, Huitong, et al.
Veröffentlicht: (2024)

WW-FL: Secure and Private Large-Scale Federated Learning
von: Marx, Felix, et al.
Veröffentlicht: (2023)

FL-Defender: Combating Targeted Attacks in Federated Learning
von: Jebreel, Najeeb, et al.
Veröffentlicht: (2022)

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
von: Zhou, Yvonne, et al.
Veröffentlicht: (2024)

Differentially Private Tabular Data Synthesis using Large Language Models
von: Tran, Toan V., et al.
Veröffentlicht: (2024)

Differentially Private Federated Learning without Noise Addition: When is it Possible?
von: Zhang, Jiang, et al.
Veröffentlicht: (2024)

ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterations
von: Ling, Xinpeng, et al.
Veröffentlicht: (2023)

Scaling Laws for Differentially Private Language Models
von: McKenna, Ryan, et al.
Veröffentlicht: (2025)

FuSeFL: Fully Secure and Scalable Federated Learning
von: Ghinani, Sahar Ghoflsaz, et al.
Veröffentlicht: (2025)

On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps
von: Heikkilä, Mikko A.
Veröffentlicht: (2024)

Differentially Private Selection using Smooth Sensitivity
von: Chaves, Iago, et al.
Veröffentlicht: (2025)

HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
von: Khan, Momin Ahmad, et al.
Veröffentlicht: (2024)

Meta-FL: A Novel Meta-Learning Framework for Optimizing Heterogeneous Model Aggregation in Federated Learning
von: Alsulaimawi, Zahir
Veröffentlicht: (2024)

Exactly Minimax-Optimal Locally Differentially Private Sampling
von: Park, Hyun-Young, et al.
Veröffentlicht: (2024)

Efficient Language Model Architectures for Differentially Private Federated Learning
von: Ro, Jae Hun, et al.
Veröffentlicht: (2024)

Differentially Private E-Values
von: Csillag, Daniel, et al.
Veröffentlicht: (2025)

Federated Discrete Denoising Diffusion Model for Molecular Generation with OpenFL
von: Ta, Kevin, et al.
Veröffentlicht: (2025)

Differentially Private Synthetic Data Generation for Relational Databases
von: Alimohammadi, Kaveh, et al.
Veröffentlicht: (2024)

Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
von: Xu, Jie, et al.
Veröffentlicht: (2026)

Privately Aligning Language Models with Reinforcement Learning
von: Wu, Fan, et al.
Veröffentlicht: (2023)

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
von: Tramèr, Florian, et al.
Veröffentlicht: (2022)

Oracle-Efficient Differentially Private Learning with Public Data
von: Block, Adam, et al.
Veröffentlicht: (2024)

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
von: Wei, Jianxin, et al.
Veröffentlicht: (2022)

Differentially Private Sampling from Distributions via Wasserstein Projection
von: Takakura, Shokichi, et al.
Veröffentlicht: (2026)

Differentially Private Diffusion Models
von: Dockhorn, Tim, et al.
Veröffentlicht: (2022)

Differentially Private Next-Token Prediction of Large Language Models
von: Flemings, James, et al.
Veröffentlicht: (2024)

Privately Learning Decision Lists and a Differentially Private Winnow
von: Bun, Mark, et al.
Veröffentlicht: (2026)

SPriFed-OMP: A Differentially Private Federated Learning Algorithm for Sparse Basis Recovery
von: Mulay, Ajinkya Kiran, et al.
Veröffentlicht: (2024)

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers and Gradient Clipping
von: Pelikan, Martin, et al.
Veröffentlicht: (2023)

FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning
von: Yang, Yanxin, et al.
Veröffentlicht: (2023)

Differentially Private Federated $k$-Means Clustering with Server-Side Data
von: Scott, Jonathan, et al.
Veröffentlicht: (2025)