Optimized feature selection and zero-parameter channel attention BiLSTM for RPL-attack classification in IoT networks
Sudha Rani Unnam, Kareemulla Shaik · 2026
Read Optimized feature selection and zero-parameter channel attention BiLSTM for RPL-attack classification in IoT networks by Sudha Rani Unnam, Kareemulla Shaik (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/PMC13278453.txt.
Description
Sudha Rani Unnam and Kareemulla Shaik present a 2026 study of a deep learning system that detects routing attacks in Internet of Things networks. Such networks link many small devices, and their low-power routing protocol is a target for attacks such as blackhole and flooding. The framework first selects the most useful data features with an optimization algorithm, then classifies attacks with a memory-based neural network.
On a standard attack dataset covering four attack types, the system reached about ninety-nine percent accuracy with a low false discovery rate. It beat baseline models in comparison tests. The authors note two limits: the evaluation rests on simulated data, and training adds computing cost that may hinder real-time use on small devices.
Catalog record
| CREATOR | Sudha Rani Unnam, Kareemulla Shaik |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70251 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |