Lightweight and Energy-Aware Intrusion Detection for Industrial IoT Using TinyML and Edge AI
Laila Nassef, Mohammed Ibrahim Alghamdi, Slim BEN CHAABANE, Qaisar Abbas, Wedad M. Alawad, Omar H Albalawi, Osamah I. Alqaisi, Bahjat Fakieh · 2026
Read Lightweight and Energy-Aware Intrusion Detection for Industrial IoT Using TinyML and Edge AI by Laila Nassef, Mohammed Ibrahim Alghamdi, Slim BEN CHAABANE, Qaisar Abbas, Wedad M. Alawad, Omar H Albalawi, Osamah I. Alqaisi, Bahjat Fakieh (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13269888.txt.
Description
Laila Nassef and co-authors published a journal article in 2026 on a lightweight security system for industrial internet devices, which face growing cyber attacks. Their design mixes a graph attention network, which weighs links between devices, with a memory network that reads traffic in both directions. Training is shared across devices without moving private data.
A wolf-inspired optimizer tuned the system faster than older methods. In a ten-node simulation, shared training cut communication load by 20 percent. Detection accuracy reached up to 95 percent across attack types, including denial-of-service floods and zero-day exploits. Best scores on three standard datasets reached 0.94 on a balanced accuracy measure. An explanation module shows why alerts fire.
Catalog record
| CREATOR | Laila Nassef, Mohammed Ibrahim Alghamdi, Slim BEN CHAABANE, Qaisar Abbas, Wedad M. Alawad, Omar H Albalawi, Osamah I. Alqaisi, Bahjat Fakieh |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 112781 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |