Multi-Tentacle Federated Learning over Software-Defined Industrial Internet of Things Against Adaptive Poisoning Attacks

Gaolei Li, Jun Wu, Shenghong Li, Wu Yang, Changlian Li

Research output: Contribution to journalArticlepeer-review


Software-defined industrial Internet of things (SD-IIoT) exploits federated learning to process the sensitive data at edges, while adaptive poisoning attacks threat the security of SD-IIoT. To address this problem, this paper proposes a multi-tentacle federated learning (MTFL) framework, which is essential to guarantee the trustness of training data in SD-IIoT. In MTFL, participants with similar learning tasks are assigned to the same tentacle group. To identify adaptive poisoning attacks, a tentacle distribution-based efficient poisoning attack detection (TD-EPAD) algorithm is presented. And also, to minimize the impact of adaptive poisoning data, a stochastic tentacle data exchanging (STDE) protocol is also proposed. Simultaneously, to protect the tentacle's privacy in STDE, all exchanged data will be processed by differential privacy technology. A MTFL prototype system is implemented, which provides extensive ablation experiments and comparison experiments, demonstrating that the accuracy of the global model under attack scenario can be improved with 40%.

Original languageEnglish
Pages (from-to)1
Number of pages1
JournalIEEE Transactions on Industrial Informatics
Publication statusAccepted/In press - 2022


  • Adaptation models
  • Collaborative work
  • Data models
  • Differential Privacy
  • Industrial Internet of Things
  • Informatics
  • Multi-Tentacle Federated Learning
  • Poisoning Attacks
  • Protocols
  • Software-Defined Industrial Internet of Things (SD-IIoT)
  • Training

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Multi-Tentacle Federated Learning over Software-Defined Industrial Internet of Things Against Adaptive Poisoning Attacks'. Together they form a unique fingerprint.

Cite this