Reservoir computing for network intrusion classification
Khorshed Alam, Mahbubul Haq Bhuiyan, Mohammad Ashraful Hoque, Mohammad Shohel Rana, Dewan Md Farid · 2026
Read Reservoir computing for network intrusion classification by Khorshed Alam, Mahbubul Haq Bhuiyan, Mohammad Ashraful Hoque, Mohammad Shohel Rana, Dewan Md Farid (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/plos-pone-0355211.txt.
Description
Khorshed Alam and co-authors tested brain-inspired computing for spotting intrusions on networks of small connected devices. Such devices cannot run heavy security software, so detection must be light. Their 2026 study built detectors on reservoir computing, where a fixed recurrent pool does most of the work and training stays minimal.
The team tried two reservoir designs on a recent dataset of well over a million network flows, covering many attack types. Both designs performed close to the standard deep learning models used for comparison. They did so while using far fewer computing resources. Alam and colleagues argue reservoir models deserve more attention as a fast, lean option for guarding device networks in real time.
Catalog record
| CREATOR | Khorshed Alam, Mahbubul Haq Bhuiyan, Mohammad Ashraful Hoque, Mohammad Shohel Rana, Dewan Md Farid |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51086 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |