Robustness, Cost, and Attack-Surface Concentration in Phishing Detection

ArXi:2603.19204v1 Announce Type: new Phishing detectors built on engineered website features attain near-perfect accuracy under i.i.d.\ evaluation, yet deployment security depends on robustness to post-deployment feature manipulation. We study this gap through a cost-aware evasion framework that models discrete, monotone feature edits under explicit attacker budgets.