paperSeptember 2026Unreviewed

Efficient Prompt Security Detection for LLM Service Deployment in Edge-Cloud Networks

Wen-Jing Chen, Jie Cui, Wenjie Huang, Jing Zhang, Lu Wei, Geyong Min

IEEE Transactions on Dependable and Secure Computing

Abstract

While Large Language Models (LLMs) have achieved revolutionary advancements in natural language processing, their inherent vulnerability to prompt injection attacks has raised significant security concerns. Existing security detection approaches for LLM deployment often fail to fully leverage edge-cloud collaboration and largely overlook the issue of user heterogeneity, resulting in reduced detection efficiency and security risks. To address these challenges, this paper proposes a Belief-updatin

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@article{chen2026efficient,
  title = {{Efficient Prompt Security Detection for LLM Service Deployment in Edge-Cloud Networks}},
  author = {Wen-Jing Chen and Jie Cui and Wenjie Huang and Jing Zhang and Lu Wei and Geyong Min},
  year = {2026},
  month = sep,
  journal = {IEEE Transactions on Dependable and Secure Computing},
  doi = {10.1109/TDSC.2026.3709894},
  url = {https://www.semanticscholar.org/paper/084aed427d1488610dcf103935fe66ad361ee86d}
}