FGLBA: Enabling Highly-Effective and Stealthy Backdoor Attack on Federated Graph Learning - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Qing Lu, Miao Hu 0001, Di Wu 0001, Yipeng Zhou, Mohsen Guizani, Quan Z. Sheng. FGLBA: Enabling Highly-Effective and Stealthy Backdoor Attack on Federated Graph Learning. In Elena Baralis, Kun Zhang 0001, Ernesto Damiani, Mérouane Debbah, Panos Kalnis, Xindong Wu 0001, editors, IEEE International Conference on Data Mining, ICDM 2024, Abu Dhabi, United Arab Emirates, December 9-12, 2024. pages 791-796, IEEE, 2024. [doi]

The following publications are possibly variants of this publication:

Distributed Swift and Stealthy Backdoor Attack on Federated LearningAgnideven Palanisamy Sundar, Feng Li 0001, Xukai Zou, Tianchong Gao. nas 2022: 1-8 [doi]

Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated LearningXiaoting Lyu, Yufei Han, Wei Wang 0012, Jingkai Liu, Yongsheng Zhu, Guangquan Xu, Jiqiang Liu, Xiangliang Zhang 0001. uss 2024: [doi]

SemSBA: Semantic-perturbed Stealthy Backdoor Attack on Federated Semi-supervised LearningYingrui Tong, Jun Feng, Gaolei Li, Xi Lin 0003, Chengcheng Zhao, Xiaoyu Yi, Jianhua Li 0001. icpads 2023: 1569-1576 [doi]

Poisoning with Cerberus: Stealthy and Colluded Backdoor Attack against Federated LearningXiaoting Lyu, Yufei Han, Wei Wang, Jingkai Liu, Bin Wang, Jiqiang Liu, Xiangliang Zhang 0001. AAAI 2023: 9020-9028 [doi]

Stealthy Backdoors in Vertical Federated LearningXu Yang, Yuchuan Luo, Shaojing Fu, Ming Xu 0001. icic 2025: 227-238 [doi]

runs on WebDSL