Self-Supervised Behavioral Risk Monitoring for Large Language Models in Edge Intelligence Environments
Journal of AI Analytics and Applications · 30.09.2025 · 3 (3) · 1-18
DOI: 10.63646/jaiaa.2025.030301 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of AI Analytics and Applications, online erschienen am 30.09.2025. Verfasst von Yifan Chen und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This article develops a technical framework for self-supervised behavioral risk monitoring of large language models deployed in edge intelligence environments. Inspired by recent work on deception detection for Edge-of-Things systems, the paper broadens the problem from narrow deception labels to a wider class of trust failures that include concealed unsafe plans, hallucinated justifications, unstable tool use, retrieval mismatch, and context-dependent policy evasion. The core argument is that trustworthy edge deployment requires more than compressed inference; it requires a native monitoring layer that can transform local reasoning traces, uncertainty cues, and tool telemetry into actionable risk signals without relying continuously on cloud-based judge models. The paper synthesizes research on edge computing, language-model alignment, quantization, chain-of-thought reasoning, retrieval augmentation, and intrusion detection, and uses that synthesis to propose a layered architecture composed of a primary reasoning model, a lightweight monitor head, a telemetry collector, and a policy guard. It further outlines implementation pathways, evaluation metrics, and governance implications for privacy-sensitive and latency-critical domains. The contribution lies in showing how self-supervised trust monitoring can become a practical design pattern for edge AI when computational efficiency, behavioral reliability, and organizational accountability are engineered together.
Zitieren
APA
Chen, Y., & Al-Najjar, I. (2025). Self-Supervised Behavioral Risk Monitoring for Large Language Models in Edge Intelligence Environments. Journal of AI Analytics and Applications, 3(3), 1-18. https://doi.org/10.63646/jaiaa.2025.030301
Vancouver
Chen Y, Al-Najjar I. Self-Supervised Behavioral Risk Monitoring for Large Language Models in Edge Intelligence Environments. Journal of AI Analytics and Applications. 2025;3(3):1-18. doi:10.63646/jaiaa.2025.030301
BibTeX
@article{Chen2025,
author = {Chen, Yifan and Al-Najjar, Ibrahim},
title = {Self-Supervised Behavioral Risk Monitoring for Large Language Models in Edge Intelligence Environments},
journal = {Journal of AI Analytics and Applications},
year = {2025},
volume = {3},
number = {3},
pages = {1--18},
doi = {10.63646/jaiaa.2025.030301}
}
EUVIMED