Privacy-preserving intrusion detection in IoT smart homes using a federated hybrid 1D-CNN–LSTM model with explainable AI
Ghada Abdelhady, Karim Wael Hussein, Islam Anwar Ali Gad · 2026
Read Privacy-preserving intrusion detection in IoT smart homes using a federated hybrid 1D-CNN–LSTM model with explainable AI by Ghada Abdelhady, Karim Wael Hussein, Islam Anwar Ali Gad (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/pmc-13538480.txt.
Description
Ghada Abdelhady, Karim Wael Hussein, and Islam Anwar Ali Gad present FedShield-IDS, a system to spot intrusions in smart homes without gathering private data in one place. Their 2026 paper notes that connected home devices widen the scope for botnet and denial-of-service attacks.
Central detectors raise privacy risks, form a single point of failure, and cost a lot to run. Their design uses federated learning, so models train where the data live. A hybrid model joins a one-dimensional convolutional network with long short-term memory units to catch both spatial patterns and time order in traffic. Explainable AI tools are added so users can see why an alert fired.
Catalog record
| CREATOR | Ghada Abdelhady, Karim Wael Hussein, Islam Anwar Ali Gad |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 95 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |