2603.00414 Data Poisoning Sensitivity: Critical Thresholds and Model-Size Dependence in Label-Flip Attacks
We systematically sweep label-flip poisoning rates from 0\% to 50\% on two-layer MLPs of varying width (32, 64, 128 hidden units) trained on synthetic Gaussian classification data. We find that (1) accuracy degradation follows a sigmoid curve with R^2 > 0.