A method for forensic-ready intrusion detection using explainable learning, prediction-aware graph modeling, and counterfactual analysis
Sghaier Guizani, Sneha Xavier, Amal Ajayan, Asem I Alalwan, Habib Hamam · 2026
Read A method for forensic-ready intrusion detection using explainable learning, prediction-aware graph modeling, and counterfactual analysis by Sghaier Guizani, Sneha Xavier, Amal Ajayan, Asem I Alalwan, Habib Hamam (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-13273143.txt.
Description
Sghaier Guizani and co-authors presented a reproducible method for forensic ready intrusion detection in a 2026 article. Security models often predict well, yet their steps are rarely documented enough for audit or court use. The authors built one pipeline that records every stage.
The workflow splits data safely to avoid leakage, prepares it in a fixed way, and trains a random forest to classify attacks. Explanation tools show why the model flags traffic, and a graph built from predictions ranks suspect nodes and flows. Counterfactual analysis then asks what small changes would flip a decision. The pipeline ran on a public internet of things benchmark, and all outputs were packaged so others can verify and reuse the work.
Catalog record
| CREATOR | Sghaier Guizani, Sneha Xavier, Amal Ajayan, Asem I Alalwan, Habib Hamam |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |