The Agentic AI Framework (AAIF): a policy-enforced architecture for accountable and high-performance intrusion detection
Ibrahim Adabara, Bashir Olaniyi Sadiq, Aliyu Nuhu Shuaibu, Yale Ibrahim Danjuma, Venkateswarlu Maninti, Mutebi Joe · 2026
Read The Agentic AI Framework (AAIF): a policy-enforced architecture for accountable and high-performance intrusion detection by Ibrahim Adabara, Bashir Olaniyi Sadiq, Aliyu Nuhu Shuaibu, Yale Ibrahim Danjuma, Venkateswarlu Maninti, Mutebi Joe (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-13275711.txt.
Description
Ibrahim Adabara and co-authors propose a policy-enforced AI framework for network intrusion detection in a 2026 study. Security AI often chases accuracy while offering little accountability or rule compliance. Their design pairs a deep learning detector with a governance layer tied to the NIST AI risk framework.
A policy engine written in a plain declarative language checks each decision against set rules. Tests used a public dataset holding more than two million network flow records. Detection performance matched standard baselines while every decision met the policy schema. Governance scores also rose, which the authors present as evidence that accountable automation need not cost detection power.
Catalog record
| CREATOR | Ibrahim Adabara, Bashir Olaniyi Sadiq, Aliyu Nuhu Shuaibu, Yale Ibrahim Danjuma, Venkateswarlu Maninti, Mutebi Joe |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 73 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |