RobustnessMetrics<T>

Models & Types · AiDotNet.Models

Contains metrics for evaluating adversarial robustness of models.

Constructors

Constructor Summary
RobustnessMetrics()

Properties

Property Summary
Dictionary<string, double> AdditionalMetrics { get; set; } Gets or sets additional evaluation metrics.
double AdversarialAccuracy { get; set; } Gets or sets the accuracy on adversarial examples.
double AttackSuccessRate { get; set; } Gets or sets the attack success rate (percentage of successful attacks).
double AveragePerturbationSize { get; set; } Gets or sets the average perturbation size needed to fool the model.
double CleanAccuracy { get; set; } Gets or sets the accuracy on clean (non-adversarial) examples.
double RobustnessScore { get; set; } Gets or sets the robustness score (combines clean and adversarial accuracy).