FGSM (White-Box Attack)

FGSM(; epsilon=0.1)

Subtype of WhiteBoxAttack. A struct that can be used to create a White-box Adversarial Attack using the Fast Gradient Sign Method. Based on Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572.

Arguments

• epsilon: Step size used to scale the sign of the gradient. Defaults to 0.1.

attack(atk::FGSM, model, sample; loss, detailed_result)

Perform a Fast Gradient Sign Method (FGSM) White-box Adversarial Attack on the given model using the provided sample.

Arguments

• atk::FGSM: An instance of the FGSM.
• model::FluxModel: The machine learning (deep learning) model to be attacked.
• sample: Input sample as a named tuple with data and label.
• loss: Loss function with signature loss(model, x, y). Defaults to default_loss, i.e. cross-entropy.
• detailed_result::Bool=false: Return format control.
  • false (default): Returns adversarial example only (Array).
  • true: Returns NamedTuple with metrics (xadv, success, queriesused, final_label).

Returns

• If detailed_result=false:
  • Adversarial example (same type and shape as sample.data).
• If detailed_result=true:
  • NamedTuple with fields:
    • x_adv: Adversarial example.
    • queries_used::Int: Number of gradient evaluations (for FGSM == 1).