Privacy Preserving Federated Learning

Privacy-preserving federated learning (PFL) aims to enable collaborative model training across multiple parties without directly sharing sensitive data, addressing crucial privacy concerns in distributed machine learning. Current research focuses on mitigating information leakage from shared model updates through techniques like differential privacy, homomorphic encryption, and novel algorithmic designs such as system immersion and selective quantization, often applied within various neural network architectures including LSTMs and convolutional networks. PFL's significance lies in its potential to unlock the power of large, distributed datasets for training advanced AI models across diverse sectors like healthcare and finance while upholding data privacy regulations and ethical considerations.

Papers

November 6, 2024

NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA
Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aurélie Joseph, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota, Ragul N, Rintu Kutum, Josep Llados, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
Differential Privacy Competition Platform 3d Vqa Document Analysis Privacy Preserving Federated Learning

September 25, 2024

Immersion and Invariance-based Coding for Privacy-Preserving Federated Learning
Haleh Hayati, Carlos Murguia, Nathan van de Wouw
Differential Privacy PRIvacy Leakage Privacy Preserving Federated Learning Narrative Immersion

July 23, 2024

Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theory
Xiaojin Zhang, Wei Chen
Federated Learning Theoretical Analysis PRIvacy Leakage Privacy Attack Privacy Preserving Federated Learning Data Reconstruction Attack Linear Algebra

July 18, 2024

Privacy-preserving gradient-based fair federated learning
Janis Adamek, Moritz Schulze Darup
LeArning Abstract Homomorphic Encryption Privacy Preserving Federated Learning Collaborative Fairness

June 18, 2024

Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation
Nikolas Koutsoubis, Yasin Yilmaz, Ravi P. Ramachandran, Matthew Schabath, Ghulam Rasool
Machine Learning Medical Image Uncertainty Estimation Medical Imaging Privacy Preserving Federated Learning

May 9, 2024

Privacy-Preserving Edge Federated Learning for Intelligent Mobile-Health Systems
Amin Aminifar, Matin Shokri, Amir Aminifar
Machine Learning Federated Edge Learning Privacy Preserving Federated Learning Intelligent Healthcare Wearable Technology

April 29, 2024

Bridging Data Barriers among Participants: Assessing the Potential of Geoenergy through Federated Learning
Weike Peng, Jiaxin Gao, Yuntian Chen, Shengwei Wang
Bayesian Optimization Full Potential Hyperparameter Tuning XGBoost Model Privacy Preserving Federated Learning Participant State Data Challenge Geothermal Resource Centralized Model

February 19, 2024

Secure Federated Learning Across Heterogeneous Cloud and High-Performance Computing Resources -- A Case Study on Federated Fine-tuning of LLaMA 2
Zilinghan Li, Shilan He, Pranshu Chaturvedi, Volodymyr Kindratenko, Eliu A Huerta, Kibaek Kim, Ravi Madduri
Fine Tuning Federated Learning Heterogeneous Computing LLaMa LlamaCare Privacy Preserving Federated Learning Local Datasets

January 22, 2024

Privacy-Preserving Data Fusion for Traffic State Estimation: A Vertical Federated Learning Approach
Qiqing Wang, Kaidi Yang
Privacy Preserving Vertical Federated Learning Private Data Information Fusion Privacy Preserving Federated Learning Traffic Model Traffic State Estimation

January 19, 2024

Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detection
Aydin Abadi, Bradley Doyle, Francesco Gini, Kieron Guinamard, Sasi Kumar Murakonda, Jack Liddell, Paul Mellor, Steven J. Murdoch, Mohammad Naseri, Hector Page, George Theodorakopoulos, Suzanne Weller
Homomorphic Encryption Privacy Preserving Federated Learning Financial Fraud Detection Modular Addition

October 11, 2023

Histopathological Image Classification and Vulnerability Analysis using Federated Learning
Sankalp Vyas, Amar Nath Patra, Raj Mani Shukla
Machine Learning Image Classification Data Poisoning Attack Data Privacy Data Poisoning Privacy Preserving Federated Learning Vulnerability Analysis

October 10, 2023

Federated Learning with Reduced Information Leakage and Computation
Tongxin Yin, Xuwei Tan, Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
Computation Method Heterogeneous Data Data Leakage Privacy Preserving Federated Learning Privacy Accuracy

September 8, 2023

Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks
Daniel Scheliga, Patrick Mäder, Marco Seeland
Gradient Inversion Attack Privacy Preserving Federated Learning Gradient Leakage Gradient Leakage Attack Variational Bottleneck

September 4, 2023

Secure and Efficient Federated Learning in LEO Constellations using Decentralized Key Generation and On-Orbit Model Aggregation
Mohamed Elmahallawy, Tie Luo, Mohamed I. Ibrahem
Federated Learning Secure Approach Privacy Preserving Federated Learning Satellite Data Orbit Model

July 30, 2023

Shuffled Differentially Private Federated Learning for Time Series Data Analytics
Chenxi Huang, Chaoyang Jiang, Zhenghua Chen
Time Series Local Differential Privacy Private Federated Learning Privacy Amplification Time Series Datasets Privacy Preserving Federated Learning

May 24, 2023

Theoretically Principled Federated Learning for Balancing Privacy and Utility
Xiaojin Zhang, Wenjie Li, Kai Chen, Shutao Xia, Qiang Yang
Task Utility Empirical Privacy Privacy Preserving Federated Learning Optimal Hyperparameters Utility Privacy Trade

May 2, 2023

Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing
Yifan Shi, Kang Wei, Li Shen, Jun Li, Xueqian Wang, Bo Yuan, Song Guo
Differential Privacy Federated Learning Edge Computing Decentralized Data Privacy Preservation Privacy Preserving Federated Learning

October 16, 2022

Federated Learning with Privacy-Preserving Ensemble Attention Distillation
Xuan Gong, Liangchen Song, Rishi Vedula, Abhishek Sharma, Meng Zheng, Benjamin Planche, Arun Innanje, Terrence Chen, Junsong Yuan, David Doermann, Ziyan Wu
PRIvacy Leakage Privacy Preserving Federated Learning Privacy Mechanism Attention Distillation

September 23, 2022

Privacy-Preserving Online Content Moderation: A Federated Learning Use Case
Pantelitsa Leonidou, Nicolas Kourtellis, Nikos Salamanos, Michael Sirivianos
Differential Privacy Federated Learning Privacy Preserving Federated Learning Online Content Moderation

June 30, 2022

Towards Federated Long-Tailed Learning
Zihan Chen, Songshang Liu, Hualiang Wang, Howard H. Yang, Tony Q. S. Quek, Zuozhu Liu
Long Tailed Learning Long Tailed Data Privacy Preserving Federated Learning

Privacy Preserving Federated Learning

Papers

NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA

Immersion and Invariance-based Coding for Privacy-Preserving Federated Learning

Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theory

Privacy-preserving gradient-based fair federated learning

Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation

Privacy-Preserving Edge Federated Learning for Intelligent Mobile-Health Systems

Bridging Data Barriers among Participants: Assessing the Potential of Geoenergy through Federated Learning

Secure Federated Learning Across Heterogeneous Cloud and High-Performance Computing Resources -- A Case Study on Federated Fine-tuning of LLaMA 2

Privacy-Preserving Data Fusion for Traffic State Estimation: A Vertical Federated Learning Approach

Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detection

Histopathological Image Classification and Vulnerability Analysis using Federated Learning

Federated Learning with Reduced Information Leakage and Computation

Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks

Secure and Efficient Federated Learning in LEO Constellations using Decentralized Key Generation and On-Orbit Model Aggregation

Shuffled Differentially Private Federated Learning for Time Series Data Analytics

Theoretically Principled Federated Learning for Balancing Privacy and Utility

Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing

Federated Learning with Privacy-Preserving Ensemble Attention Distillation

Privacy-Preserving Online Content Moderation: A Federated Learning Use Case

Towards Federated Long-Tailed Learning