Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning

no code implementations • 10 Jun 2024 • Xiaoting Lyu, Yufei Han, Wei Wang, Jingkai Liu, Yongsheng Zhu, Guangquan Xu, Jiqiang Liu, Xiangliang Zhang

Furthermore, PFL systems can also deploy both server-end and client-end defense mechanisms to strengthen the barrier against backdoor attacks.

Backdoor Attack Personalized Federated Learning

Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience

no code implementations • 12 Jun 2023 • Ao Liu, Wenshan Li, Tao Li, Beibei Li, Guangquan Xu, Pan Zhou, Wengang Ma, Hanyuan Huang

In this paper, we propose the Graph Agent Network (GAgN) to address the aforementioned vulnerabilities of GNNs.

Classification Node Classification

OFEI: A Semi-black-box Android Adversarial Sample Attack Framework Against DLaaS

no code implementations • 25 May 2021 • Guangquan Xu, GuoHua Xin, Litao Jiao, Jian Liu, Shaoying Liu, Meiqi Feng, Xi Zheng

With the growing popularity of Android devices, Android malware is seriously threatening the safety of users.

DynaComm: Accelerating Distributed CNN Training between Edges and Clouds through Dynamic Communication Scheduling

no code implementations • 20 Jan 2021 • Shangming Cai, Dongsheng Wang, Haixia Wang, Yongqiang Lyu, Guangquan Xu, Xi Zheng, Athanasios V. Vasilakos

To reduce uploading bandwidth and address privacy concerns, deep learning at the network edge has been an emerging topic.

Scheduling

Big Data Analytics for Manufacturing Internet of Things: Opportunities, Challenges and Enabling Technologies

no code implementations • 1 Sep 2019 • Hong-Ning Dai, Hao Wang, Guangquan Xu, Jiafu Wan, Muhammad Imran

The recent advances in information and communication technology (ICT) have promoted the evolution of conventional computer-aided manufacturing industry to smart data-driven manufacturing.