Additive

Add a configured amount to each tabular feature value.

Required inputs

A model, evaluation data, a baseline result and the selected transformation or attack settings. Adversarial attacks require a compatible image model.

Establish the baseline, apply the selected perturbation and rerun the task metric under the changed conditions.

Baseline[x₁, x₂, …]Model

Additive condition[x₁ + ε, x₂ + ε, …]Model

Compare results

Each feature value becomes x + ε before inference. Compare the changed-condition measurements with their matching baseline.

Compare the perturbed result with the baseline and inspect affected examples. Judge the change against conditions plausible for your use case.

Keep the baseline, perturbation configuration, changed examples and resulting performance comparison together.