paperSeptember 2026Unreviewed

Delayed Backdoor: Let the Trigger Fly for a While in Backdoor Attack on Internet of Things

Bo Liu, Pei-Wen Zhu, Shao-Feng Zhao, Xiang Chen, Hao-Jie Huang, Li-Ling Shi, Xiao-Kang Wang, Zhi-Gao Zheng, Laurence T. Yang

IEEE Internet of Things Journal

View resource

Abstract

Since large language models (LLMs) have gained wide attention as the core of AI agents in the Internet of Things (IoT) for conversation and generation tasks, their security issues have become more prominent, especially regarding backdoor attacks. Traditional backdoor attacks often rely on fixed triggers and static outputs, failing to fully exploit the conversational characteristics and generativity of LLMs, which limits their stealth and attack effectiveness in complex human–agent interactions.

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

Suggested from the entry's categories.

Cite

@article{liu2026delayed,
  title = {{Delayed Backdoor: Let the Trigger Fly for a While in Backdoor Attack on Internet of Things}},
  author = {Bo Liu and Pei-Wen Zhu and Shao-Feng Zhao and Xiang Chen and Hao-Jie Huang and Li-Ling Shi and Xiao-Kang Wang and Zhi-Gao Zheng and Laurence T. Yang},
  year = {2026},
  month = sep,
  journal = {IEEE Internet of Things Journal},
  doi = {10.1109/JIOT.2026.3686078},
  url = {https://www.semanticscholar.org/paper/b550cd95248dfd0d0c4a44b015958170793ffbb5}
}