Hybrid AI Intrusion Detection: Balancing Accuracy and Efficiency
Vandit R Joshi, Kwame Assa-Agyei, Tawfik Al-Hadhrami, Sultan Noman Qasem · 2025
Read Hybrid AI Intrusion Detection: Balancing Accuracy and Efficiency by Vandit R Joshi, Kwame Assa-Agyei, Tawfik Al-Hadhrami, Sultan Noman Qasem (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-12736922.txt.
Description
Vandit Joshi, Kwame Assa-Agyei, Tawfik Al-Hadhrami, and Sultan Qasem compare three artificial intelligence models for spotting intrusions in internet of things networks, in a study from 2025. Connected devices are numerous, weak, and varied, which breaks the assumptions of older alarm systems. False alarms and slow reactions are chronic problems in this setting.
The team benchmarked a deep hybrid network, a random forest, and a gradient boosting model on two standard attack data sets. The deep model reached the strongest detection scores but answered slowest. The tree based models traded a little accuracy for much faster replies. Laying the trade bare helps builders pick a model by setting: tight watch where accuracy rules, lean models where milliseconds count.
Catalog record
| CREATOR | Vandit R Joshi, Kwame Assa-Agyei, Tawfik Al-Hadhrami, Sultan Noman Qasem |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |