Evaluating Prompt Injection Risk and Guardrails in LLM-Enabled Home IoT Assistants

Abstract

Smart home virtual assistants are increasingly powered by large language models to enable information retrieval and home device actuation. As a result, intelligent home environments are becoming more exposed to untrusted inputs, increasing their susceptibility to prompt injection, role confusion, and indirect prompt injection through retrieved context. In this paper, we propose a layered architecture that separates LLM-driven intent interpretation from the authorization and safety enforcement me

Categories

Framework mappings

Suggested from the entry's categories.

@inproceedings{zaman2026evaluating,
  title = {{Evaluating Prompt Injection Risk and Guardrails in LLM-Enabled Home IoT Assistants}},
  author = {Shazid Bin Zaman and Sohan Gyawali and C. Popoviciu and Yi-Li Jiang and Jiaqi Huang},
  year = {2026},
  month = aug,
  booktitle = {2026 International Conference on Intelligent Multimedia, Networking, and Security (IMNS)},
  doi = {10.1109/IMNS67862.2026.11655283},
  url = {https://www.semanticscholar.org/paper/a374a751e5fd33edaee8fdcabeac3ef8f5ea590d}
}