Code for the research "FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning"

This research aims to investigate the vulnerabilities of existing federated learning frameworks against backdoor attacks and to develop a novel backdooring approach. The study focuses on advancing a new technology in this area. The research uses textual data, with all data (i.e., source code) being independently developed.

本研究旨在探究现有联邦学习（Federated Learning）框架在应对后门攻击（Backdoor Attack）时存在的安全脆弱性，并开发一种全新的后门攻击方法。本研究聚焦于推动该领域的技术革新与发展。本研究采用文本数据集，所有相关数据（即源代码）均为独立开发完成。