Attention integrated deep learning models for interpretable multi-class IoT intrusion detection using SHAP
Ramakrishnan Raman, Rahul Kumar, Benson Edwin Raj, Vishwesh Akre · 2026
Read Attention integrated deep learning models for interpretable multi-class IoT intrusion detection using SHAP by Ramakrishnan Raman, Rahul Kumar, Benson Edwin Raj, Vishwesh Akre (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-13272135.txt.
Description
Ramakrishnan Raman and coauthors build in 2026 attention-guided deep learning models that detect intrusions in Internet of Things networks and explain their verdicts. Connected devices generate huge, varied traffic where attacks hide in subtle patterns. Older rule-based detectors struggle to keep up with new attack styles.
The team compared attention-enhanced convolutional and memory-based networks on two public traffic datasets holding real benign and malicious flows. The convolutional model scored highest on both sets. An explanation method called SHAP then showed which traffic features pushed each decision, giving security staff a way to audit alerts rather than trust the model blindly.
Catalog record
| CREATOR | Ramakrishnan Raman, Rahul Kumar, Benson Edwin Raj, Vishwesh Akre |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 76 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |