Assessment of IIoT sensor security vulnerabilities in AI-driven digital manufacturing
Loading...
Supplementary material
Other Title
Authors
Sen, Sachin
Song, Lei
Song, Lei
Author ORCID Profiles (clickable)
Degree
Grantor
Date
2026-12
Supervisors
Type
Conference Contribution - Oral Presentation
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
IIoT sensors
Industrial Internet of Things (IIoT)
cyber attacks
AI in digital manufacturing
Industrial Internet of Things (IIoT)
cyber attacks
AI in digital manufacturing
Citation
Sen, S., & Song, L. (2025, December, 1-5) Assessment of IIoT sensor security vulnerabilities in AI-driven digital manufacturing [Paper presentation]. ITP Rangahau & Research Symposium 2025 + OPSITARA 2025, New Zealand.
https://hdl.handle.net/10652/7149
Abstract
The rapid adoption of Artificial Intelligence (AI) in digital manufacturing has transformed industrial operations by enabling higher levels of automation, efficiency, and adaptive decision-making. This transformation integrates Industrial Internet of Things (IIoT) sensors, which provide the critical real-time data streams that fuel AI-driven analytics and control systems. However, the increased dependence on IIoT sensors introduces new layers of cybersecurity risk. At the sensor level, vulnerabilities such as spoofing, tampering, denial-of-service, and data leakage pose significant threats, as even minor compromises can propagate through AI models and lead to severe consequences, including production downtime, reduced product quality, and safety hazards. This research presents a systematic investigation into the security vulnerabilities of IIoT sensors in AI-enabled digital manufacturing environments. Using the Common Vulnerability Scoring System (CVSS) as a quantitative framework, combined with industrial cybersecurity standards such as NIST, the study evaluates the severity of sensor-specific threats and prioritises their impact on operational resilience. The analysis emphasises how corrupted sensor data undermines the reliability of AI-driven decision models, creating a cascading effect on manufacturing processes. In addition, mitigation strategies including secure authentication, real-time anomaly detection, sensor redundancy, and data validation mechanisms are explored as pathways to strengthen defence mechanisms. The findings contribute to advancing a sensor-centric perspective of cybersecurity, highlighting the importance of proactive vulnerability assessment and targeted protection. By addressing these challenges, this work enhances the overall cyber-resilience of AI-driven digital manufacturing and supports the development of more secure, trustworthy industrial ecosystems.
Publisher
Permanent link
Link to ePress publication
DOI
Copyright holder
Authors
Copyright notice
All rights reserved