LLM-Driven Lightweight AI Intrusion Prevention System for Industrial IoT
Technology Introduction:
This technology pioneers an asymmetric AI architecture for IIoT. It uses an LLM to extract the semantics of complex industrial packets, then deploys a lightweight LSTM onto ORing's edge switches for real-time inference. Achieving a 0.99 F1-score, it blocks zero-day attacks without false positives. Additionally, its red teaming engine serves as an automated compliance tool, helping vendors meet CRA requirements and pass SEMI E187 certification.
Industrial Applications:
Resolving the critical "false positive downtime" in OT environments, our technology has integrated with leading networking manufacturer ORing, embedding edge AI directly into industrial switches with no changes to existing machinery. Additionally, our red teaming engine functions as an automated compliance testing tool. This helps Taiwanese smart manufacturing and OT equipment vendors meet CRA requirements and pass SEMI E187 certification for global market export.
National Taiwan University of Science And Technology
National Taiwan University of Science and Technology (NTUST) is Taiwan's premier university of science and technology, emphasizing innovation, engineering, design, and industry collaboration.
Contact Information
Name：Chia-Yi Chu
Tel：02-2733-3141 #7677
Address：No.43, Keelung Rd., Sec.4, Da’an Dist., Taipei 10607, Taiwan
