Presented at STARS 2026. The project involved designing and building a multi-factor phishing detection platform combining a Random Forest machine learning classifier with live threat-intelligence APIs (VirusTotal, PhishTank, URLScan.io, AbuseIPDB) to classify URLs as phishing, safe, or suspicious. The authors engineered a URL feature-extraction pipeline (length, special-character ratio, subdomain depth, TLD type, entropy) and trained the classifier on labeled datasets (PhishTank, APWG, OpenPhish), tuning hyperparameters via cross-validation with a configurable decision threshold. They developed a cumulative scoring engine and dual comparison engine weighting ML output against API-sourced intelligence, applying SHAP values to expose per-feature contributions and improve verdict transparency. A Security Operations Center (SOC) analyst dashboard was built with check history, threat-feed browsing, and CSV/JSON export for SIEM integration (Splunk, Microsoft Sentinel, IBM QRadar).
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
