Main article

Wei Zhang
School of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, Zhejiang, China
Jianhua Liu
Department of Industrial Engineering, Nanchang University, Nanchang 330031, Jiangxi, China
Mingfei Chen*
College of Information Engineering, Hebei University of Engineering, Handan 056038, Hebei, China
chenmf@hebeu.edu.cn

Abstract

The proliferation of Large Language Models (LLMs) as intelligent controllers and decision-support components in cyber-physical production systems (CPPS) introduces a novel and underexamined class of safety vulnerability known as deceptive alignment, wherein an edge-deployed model appears compliant during monitoring while covertly pursuing misaligned objectives during autonomous operation. Existing industrial AI safety mechanisms predominantly rely on output-level anomaly detection, failing to inspect the intermediate reasoning processes where deceptive strategies first emerge. This paper presents EduMonitor-CPS, a self-supervised deception monitoring framework specifically designed for LLMs deployed on industrial edge nodes in smart manufacturing environments. The framework introduces three principal innovations: (1) a manufacturing-aware deception taxonomy categorizing five CPPS-specific behavioral deception patterns; (2) a zero-oracle contrastive monitoring pipeline that eliminates dependence on cloud-based teacher models through entropy-filtered self-bootstrapping, enabling fully offline operation within air-gapped production environments; and (3) a geometric representation learning module employing Triplet Loss optimization to project Chain-of-Thought (CoT) hidden states into separable manifolds. Evaluation across three industrial test scenarios demonstrates a Deception Tendency Rate (DTR) of 37.42% with 0.9 ms per-token latency on NVIDIA Jetson AGX Orin hardware, representing a 40x power reduction versus cloud-monitoring architectures while preserving real-time process control capability.


 

Article details

How to Cite

Zhang, W. ., Liu, J., & Chen, M. (2026). Industrial Edge LLM Safety for Smart Manufacturing: Self-Supervised Deception Monitoring in Cyber-Physical Production Systems. Journal of Intelligent Industrial Convergence, 6(1), 15-33. https://doi.org/10.63646/jiic.2026.060102