Red teaming and adversarial testing in Prompt Engineering / GenAI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is red teaming in the context of AI?

Red teaming is a process where experts simulate attacks or challenges on an AI system to find weaknesses before bad actors do.

beginner

What does adversarial testing aim to do?

Adversarial testing tries to find inputs that confuse or trick an AI model, revealing its vulnerabilities.

intermediate

Why is red teaming important for AI safety?

It helps catch hidden problems early, making AI systems safer and more reliable before they are widely used.

beginner

Give an example of an adversarial input.

An image slightly changed so a model mistakes a cat for a dog is an adversarial input.

intermediate

How do red teaming and adversarial testing differ?

Red teaming is broader, including many attack types and strategies, while adversarial testing focuses on tricky inputs to fool models.

What is the main goal of red teaming in AI?

A To find and fix AI weaknesses before real attacks happen

B To train AI models faster

C To collect more data for AI

D To improve AI user interface

Red teaming aims to find and fix weaknesses in AI systems before attackers exploit them.

Which of these is an example of adversarial testing?

A Increasing training data size

B Changing input data slightly to confuse the AI

C Adding more layers to a neural network

D Deploying AI to production

Adversarial testing involves modifying inputs to trick or confuse AI models.

Why might an AI system fail when given adversarial inputs?

A Because the inputs exploit model weaknesses

B Because the AI is too slow

C Because the AI has too much data

D Because the AI is overfitting

Adversarial inputs are designed to exploit weaknesses in AI models causing failures.

Which activity is NOT part of red teaming?

A Simulating attacks on AI

B Testing AI with tricky inputs

C Improving AI user experience design

D Finding security gaps

Improving user experience is not part of red teaming, which focuses on security and robustness.

What is a key benefit of adversarial testing?

A It improves AI hardware

B It speeds up AI training

C It reduces AI model size

D It reveals hidden AI vulnerabilities

Adversarial testing helps find hidden vulnerabilities by challenging AI with tricky inputs.

Explain in your own words what red teaming is and why it matters for AI systems.

Think about how experts try to 'attack' AI to make it stronger.

Describe what adversarial testing involves and give a simple example.

Imagine changing a picture just a little to fool an AI.

Practice

1. What is the main goal of red teaming in AI?

easy

A. To find weaknesses by testing with tricky inputs

B. To train the AI model with more data

C. To improve the speed of the AI model

D. To reduce the size of the AI model

Solution

1. Step 1: Understand red teaming purpose

   Red teaming is about testing AI models with challenging inputs to find weaknesses.

2. Step 2: Compare options

   Only To find weaknesses by testing with tricky inputs matches this goal; others relate to training, speed, or size, which are unrelated.

3. Final Answer:

   To find weaknesses by testing with tricky inputs -> Option A

4. Quick Check:

   Red teaming = find weaknesses [OK]

Hint: Red teaming means testing for weaknesses with tricky inputs [OK]

Common Mistakes:

• Confusing red teaming with training
• Thinking it improves speed or size
• Assuming it fixes bugs automatically

2. Which of the following is the correct way to describe an adversarial example?

easy

A. A normal input that the model handles well

B. A training example used to improve accuracy

C. A random input unrelated to the task

D. An input designed to confuse the AI model

Solution

1. Step 1: Define adversarial example

   An adversarial example is a carefully crafted input meant to confuse or trick the AI model.

2. Step 2: Match definition to options

   An input designed to confuse the AI model matches this exactly; others describe normal, random, or training inputs.

3. Final Answer:

   An input designed to confuse the AI model -> Option D

4. Quick Check:

   Adversarial example = tricky input [OK]

Hint: Adversarial examples are tricky inputs to confuse AI [OK]

Common Mistakes:

• Thinking adversarial means normal or random input
• Confusing training data with adversarial examples
• Assuming adversarial examples improve model accuracy

3. Consider this Python code snippet for adversarial testing:

def test_model(model, inputs):
    results = []
    for inp in inputs:
        pred = model.predict(inp)
        if pred == 'safe':
            results.append(True)
        else:
            results.append(False)
    return results

inputs = ['normal', 'tricky', 'normal']
class DummyModel:
    def predict(self, x):
        return 'safe' if x == 'normal' else 'unsafe'

model = DummyModel()
print(test_model(model, inputs))

What is the output?

medium

A. [False, True, False]

B. [True, True, True]

C. [True, False, True]

D. [False, False, False]

Solution

1. Step 1: Understand model predictions

   The DummyModel returns 'safe' for 'normal' inputs and 'unsafe' for others.

2. Step 2: Evaluate each input

   Inputs are ['normal', 'tricky', 'normal']. Predictions: 'safe', 'unsafe', 'safe'. Results: True, False, True.

3. Final Answer:

   [True, False, True] -> Option C

4. Quick Check:

   Predictions match results [OK]

Hint: Check each input prediction carefully [OK]

Common Mistakes:

• Mixing up 'safe' and 'unsafe' outputs
• Assuming all inputs are safe
• Ignoring the else condition

4. This code tries to detect adversarial inputs but has a bug:

def detect_adversarial(inputs, model):
    flagged = []
    for i in inputs:
        if model.predict(i) == 'safe':
            flagged.append(i)
    return flagged

class Model:
    def predict(self, x):
        return 'unsafe' if x == 'tricky' else 'safe'

inputs = ['normal', 'tricky', 'normal']
print(detect_adversarial(inputs, Model()))

What is the bug?

medium

A. The model.predict method is missing

B. It flags safe inputs instead of unsafe ones

C. The inputs list is empty

D. The function returns a boolean instead of a list

Solution

1. Step 1: Analyze detection logic

   The function flags inputs where model.predict returns 'safe'.

2. Step 2: Check model behavior

   Model returns 'unsafe' for 'tricky', 'safe' otherwise. So safe inputs are flagged, which is wrong.

3. Final Answer:

   It flags safe inputs instead of unsafe ones -> Option B

4. Quick Check:

   Flagging logic reversed [OK]

Hint: Check if flagged inputs match unsafe cases [OK]

Common Mistakes:

• Assuming model.predict is missing
• Thinking inputs list is empty
• Confusing return types

5. You want to improve an AI chatbot's safety by using red teaming and adversarial testing. Which combined approach is best?

hard

A. Use tricky inputs to find weaknesses, then retrain with those examples

B. Ignore tricky inputs and focus on normal conversation data

C. Only test with random inputs and fix errors found

D. Reduce model size to avoid complex errors

Solution

1. Step 1: Understand red teaming and adversarial testing roles

   They find weaknesses by using tricky inputs to test the model.

2. Step 2: Combine testing with retraining

   After finding weaknesses, retraining with those examples improves safety and reliability.

3. Final Answer:

   Use tricky inputs to find weaknesses, then retrain with those examples -> Option A

4. Quick Check:

   Test + retrain = better safety [OK]

Hint: Test with tricky inputs, then retrain to fix weaknesses [OK]

Common Mistakes:

• Only testing without retraining
• Ignoring tricky inputs
• Thinking smaller models fix safety