BasicRandomSearch (Black-Box Attack)

BasicRandomSearch(; epsilon=0.1, max_iter=50, bounds=nothing, rng=Random.default_rng())

Subtype of BlackBoxAttack. Creates adversarial examples using the SimBA random search algorithm. Based on Guo, C., Gardner, J., You, Y., Wilson, A. G., & Weinberger, K. (2019, May). Simple black-box adversarial attacks. In International conference on machine learning (pp. 2484-2493). PMLR.

Arguments

• epsilon: Step size for perturbations (default: 0.1).
• max_iter: Maximum number of iterations for searching (default: 50). Each iteration randomly selects a coordinate to perturb.
• bounds: Optional vector of (lower, upper) tuples specifying per-feature bounds. If nothing, defaults to [0, 1] for all features (suitable for normalized images). For tabular data, provide bounds matching feature ranges, e.g., [(4.3, 7.9), (2.0, 4.4), ...] for Iris-like data.
• rng: Random number generator for reproducibility (default: Random.default_rng()).

attack(atk::BasicRandomSearch, model::Chain, sample; detailed_result)

Perform a Black-box Adversarial Attack on the given model using the provided sample using the Basic Random Search variant SimBA.

Arguments

• atk::BasicRandomSearch: An instance of the BasicRandomSearch (Black-box) attack.
• model::Chain: The machine learning (deep learning, classical machine learning) model to be attacked.
• sample: Input sample as a named tuple with data and label.
• 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 as sample.data).
• If detailed_result=true: NamedTuple containing:
  • x_adv: Adversarial example.
  • success::Bool: Whether attack succeeded.
  • queries_used::Int: Number of model queries.
  • final_label::Int: Final predicted class.

attack(atk::BasicRandomSearch, model::DecisionTreeClassifier, sample; detailed_result)

Perform a Black-box adversarial attack on a DecisionTreeClassifier using BasicRandomSearch (SimBA).

Arguments

• atk::BasicRandomSearch: Attack instance with epsilon and optional bounds.
• model::DecisionTreeClassifier: DecisionTree.jl classifier to attack.
• sample: NamedTuple with data and label fields.
• 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 as sample.data).
• If detailed_result=true: NamedTuple containing:
  • x_adv: Adversarial example.
  • success::Bool: Whether attack succeeded.
  • queries_used::Int: Number of model queries.
  • final_label::Int: Final predicted class.