Federated Adversarial

Federated adversarial training (FAT) aims to enhance the robustness of machine learning models trained collaboratively across decentralized datasets while preserving data privacy. Current research focuses on mitigating the challenges posed by data heterogeneity and resource constraints on edge devices, often employing techniques like adversarial training with generative models, personalized federated learning, and model partitioning strategies to improve accuracy and robustness. This field is significant for building trustworthy AI systems in sensitive applications like healthcare and security, where data privacy and model resilience against adversarial attacks are paramount.

Papers

September 24, 2024

Adversarial Federated Consensus Learning for Surface Defect Classification Under Data Heterogeneity in IIoT
Jixuan Cui, Jun Li, Zhen Mei, Yiyang Ni, Wen Chen, Zengxiang Li
Model Training Data Heterogeneity Surface Defect Detection Fusion Weight Industrial Internet of Thing Federated Adversarial

September 19, 2024

FedAT: Federated Adversarial Training for Distributed Insider Threat Detection
R G Gayathri, Atul Sajjanhar, Md Palash Uddin, Yong Xiang
Federated Adversarial Insider Threat Insider Threat Detection

September 12, 2024

FedProphet: Memory-Efficient Federated Adversarial Training via Theoretic-Robustness and Low-Inconsistency Cascade Learning
Minxue Tang, Yitu Wang, Jingyang Zhang, Louis DiValentin, Aolin Ding, Amin Hass, Yiran Chen, Hai "Helen" Li
Adversarial Robustness General Robustness Federated Adversarial Cascade Learning

June 22, 2024

Federated Adversarial Learning for Robust Autonomous Landing Runway Detection
Yi Li, Plamen Angelov, Zhengxin Yu, Alvaro Lopez Pellicer, Neeraj Suri
Adversarial Attack Adversarial Learning Federated Adversarial Airport Runway Segmentation Landing Approach Runway Detection

June 1, 2023

FACT: Federated Adversarial Cross Training
Stefan Schrod, Jonas Lippl, Andreas Schäfer, Michael Altenbuchinger
Domain Shift Source Free Domain Adaptation Federated Adversarial

May 6, 2023

Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Framework
Ruijia Wu, Yuhang Wang, Huafeng Shi, Zhipeng Yu, Yichao Wu, Ding Liang
Text to Image Diffusion Model Adversarial Perturbation Adversarial Loss Privacy Protection Federated Adversarial

March 1, 2023

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
Jianing Zhu, Jiangchao Yao, Tongliang Liu, Quanming Yao, Jianliang Xu, Bo Han
Adversarial Training Robust Model Adversarial Data Robustness Problem Federated Adversarial

February 19, 2023

Delving into the Adversarial Robustness of Federated Learning
Jie Zhang, Bo Li, Chen Chen, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chao Wu
Adversarial Training Adversarial Robustness Adversarial Vulnerability Federated Adversarial

September 8, 2022

FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices
Minxue Tang, Jianyi Zhang, Mingyuan Ma, Louis DiValentin, Aolin Ding, Amin Hassanzadeh, Hai Li, Yiran Chen
Adversarial Training Adversarial Robustness Federated Prompt Cooperation Federated Adversarial Adversarial Optimization

August 7, 2022

Federated Adversarial Learning: A Framework with Convergence Analysis
Xiaoxiao Li, Zhao Song, Jiaming Yang
Adversarial Attack New Framework Adversarial Training Adversarial Learning Model Training Convergence Analysis Federated Adversarial

June 5, 2022

Federated Adversarial Training with Transformers
Ahmed Aldahdooh, Wassim Hamidouche, Olivier Déforges
Vision Transformer Adversarial Example Transformer Megatron Decepticons Adversarial Training Transformer Model Federated Adversarial

May 30, 2022

CalFAT: Calibrated Federated Adversarial Training with Label Skewness
Chen Chen, Yuchen Liu, Xingjun Ma, Lingjuan Lyu
Adversarial Attack Adversarial Training Adversarial Robustness Label Distribution Training Instability Federated Adversarial

April 5, 2022

Federated Cross Learning for Medical Image Segmentation
Xuanang Xu, Hannah H. Deng, Tianyi Chen, Tianshu Kuang, Joshua C. Barber, Daeseung Kim, Jaime Gateno, James J. Xia, Pingkun Yan
Medical Image Segmentation Segmentation Performance Federated Adversarial Cross Inferential Network

December 20, 2021

Certified Federated Adversarial Training
Giulio Zizzo, Ambrish Rawat, Mathieu Sinn, Sergio Maffeis, Chris Hankin
Adversarial Example Adversarial Training Adversarial Robustness Federated Adversarial