Adversarial_Observation package

Submodules

Adversarial_Observation.Attacks module

class Adversarial_Observation.Attacks.Config(epsilon=0.1, attack_method='fgsm')

Bases: object

Adversarial_Observation.Attacks.compute_gradients(model, img, target_class)

Adversarial_Observation.Attacks.fgsm_attack(input_batch_data: Tensor, model: Module, input_shape: tuple, epsilon: float) → Tensor

Apply the FGSM attack to input images given a pre-trained PyTorch model.

Adversarial_Observation.Attacks.generate_adversarial_examples(input_batch_data, model, method='fgsm', **kwargs)

Adversarial_Observation.Attacks.gradient_ascent(input_image, model, input_shape, target_class, num_iterations=100, step_size=0.01)

Adversarial_Observation.Attacks.gradient_map(input_image, model, input_shape)

Adversarial_Observation.Attacks.log_metrics(success_rate, average_perturbation)

Adversarial_Observation.Attacks.visualize_adversarial_examples(original, adversarial)

Adversarial_Observation.utils module

Adversarial_Observation.utils.compute_success_rate(original_preds: Tensor, adversarial_preds: Tensor) → float

Computes the success rate of the attack, which is the fraction of adversarial examples where the model was misled (i.e., adversarial prediction does not match the original prediction).

Parameters:

• original_preds (torch.Tensor) – The original model predictions.

• adversarial_preds (torch.Tensor) – The predictions on adversarial examples.

Returns:

The success rate of the attack.

Return type:

float

Adversarial_Observation.utils.fgsm_attack(input_data: Tensor, model: Module, epsilon: float, device: device) → Tensor

Performs FGSM attack on the input data.

Parameters:

• input_data (torch.Tensor) – The original input batch.

• model (torch.nn.Module) – The model to attack.

• epsilon (float) – The perturbation magnitude.

• device (torch.device) – The device to perform the attack on (cuda or cpu).

Returns:

The adversarially perturbed batch.

Return type:

torch.Tensor

Adversarial_Observation.utils.load_MNIST_data(batch_size=32)

Loads MNIST train and test data and prepares it for evaluation.

Parameters:

batch_size (int) – The batch size for data loading.

Returns:

The training and testing data loaders.

Return type:

TrinLoader, TestLoader

Adversarial_Observation.utils.load_MNIST_model()

Loads a sequential CNN model for MNIST dataset.

Returns:

The CNN model.

Return type:

torch.nn.Module

Adversarial_Observation.utils.log_metrics(success_rate: float, avg_perturbation: float)

Logs the success rate and average perturbation of the attack.

Parameters:

• success_rate (float) – The success rate of the attack.

• avg_perturbation (float) – The average perturbation magnitude.

Adversarial_Observation.utils.seed_everything(seed: int)

Sets the seed for random number generation to ensure reproducibility.

Parameters:

seed (int) – The seed value to use.

Adversarial_Observation.utils.visualize_adversarial_examples(original_images: Tensor, adversarial_images: Tensor, original_image_path: str, adversarial_image_path: str)

Visualizes and saves the original and adversarial images side by side.

Parameters:

• original_images (torch.Tensor) – Original input images.

• adversarial_images (torch.Tensor) – Adversarially perturbed images.

• original_image_path (str) – Path to save the original images.

• adversarial_image_path (str) – Path to save the adversarial images.

Adversarial_Observation.visualize module

Adversarial_Observation.visualize.visualize_gif(filenames: List[str], output_file: str = 'output.gif') → None

Create a GIF from a list of image filenames.

Parameters:

• filenames (List[str]) – List of image filenames.

• output_file (str) – Output filename for the GIF (default: ‘output.gif’).

Returns:

None

Module contents