Orchestrating machine learning models in a swarm architecture for IoT inline malware detection
Muhammad Hanif, Ehsan Ullah Munir, Muhammad Maaz Rehan, Saima Gulzar Ahmad, Kashif Ayyub, Naeem Ramzan · 2025
Read Orchestrating machine learning models in a swarm architecture for IoT inline malware detection by Muhammad Hanif, Ehsan Ullah Munir, Muhammad Maaz Rehan, Saima Gulzar Ahmad, Kashif Ayyub, Naeem Ramzan (2025) 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-12764853.txt.
Description
Muhammad Hanif and co-authors present a swarm design that runs learning models inline to catch IoT malware, in this 2025 paper. Connected devices hold private data yet guard it poorly, making them a soft entry point for attacks. Single detectors strain at this scale.
Their design spreads detection across a coordinated swarm of models that process traffic where it flows. Tests used a standard network attack data set. A boosted-tree model inside the framework reached 93.7 percent accuracy and 95 percent precision. It beat classic methods while staying fast enough for inline use. The authors offer the swarm as end-to-end IoT protection.
Catalog record
| CREATOR | Muhammad Hanif, Ehsan Ullah Munir, Muhammad Maaz Rehan, Saima Gulzar Ahmad, Kashif Ayyub, Naeem Ramzan |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 123 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |