Red teaming and adversarial testing in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create an adversarial example by adding small noise to the input.

Prompt Engineering / GenAI

adversarial_input = original_input + [1]

Drag options to blanks, or click blank then click option'

Alabels

Bnoise

Cmodel

Dloss

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'labels' instead of noise to modify the input.

Adding the model or loss instead of noise.

Adding small noise to the original input creates an adversarial example that can fool the model.

2fill in blank

medium

Complete the code to calculate the loss used for adversarial training.

Prompt Engineering / GenAI

loss = loss_function([1], predictions)

Drag options to blanks, or click blank then click option'

Aoriginal_labels

Badversarial_labels

Cadversarial_input

Dmodel_output

Attempts:

3 left

💡 Hint

Common Mistakes

Using adversarial input or model output instead of labels.

Confusing inputs with labels.

The loss compares the model's predictions to the original labels to measure error.

3fill in blank

hard

Fix the error in the code to generate adversarial noise using gradient sign method.

Prompt Engineering / GenAI

noise = epsilon * [1](loss, input, retain_graph=True)

Drag options to blanks, or click blank then click option'

Abackward

Bzero_grad

Cdetach

Dgrad

Attempts:

3 left

💡 Hint

Common Mistakes

Using backward() instead of accessing the gradient.

Calling zero_grad() or detach() incorrectly.

The gradient of the loss with respect to the input is used to create adversarial noise.

4fill in blank

hard

Fill both blanks to create a dictionary of adversarial examples filtered by confidence score.

Prompt Engineering / GenAI

adv_examples = {input: output for input, output in dataset.items() if output [1] threshold and confidence_score(input) [2] 0.8}

Drag options to blanks, or click blank then click option'

A>

B<

C>=

D<=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' for output filtering.

Using '<' instead of '>=' for confidence filtering.

We select outputs greater than the threshold and confidence scores greater or equal to 0.8.

5fill in blank

hard

Fill all three blanks to implement adversarial training step updating model parameters.

Prompt Engineering / GenAI

optimizer.[1]()
loss = loss_function(model([2]), labels)
loss.[3]()

Drag options to blanks, or click blank then click option'

Azero_grad

Badversarial_input

Cbackward

Doriginal_input

Attempts:

3 left

💡 Hint

Common Mistakes

Not clearing gradients before backward pass.

Using original input instead of adversarial input.

Calling backward on loss incorrectly.

We clear gradients, compute loss on adversarial input, then backpropagate to update model.