0
Jump into concepts and practice - no test required
Recommended
import numpy as np from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score # Simulated dataset with labels and a 'harmful' flag X = np.random.rand(1000, 10) y = (X[:, 0] + X[:, 1] > 1).astype(int) # simple label harmful_flags = (X[:, 2] > 0.8).astype(int) # simulate harmful outputs # Split data X_train, X_val, y_train, y_val, harmful_train, harmful_val = train_test_split( X, y, harmful_flags, test_size=0.2, random_state=42 ) # Simple model: logistic regression from sklearn.linear_model import LogisticRegression model = LogisticRegression(max_iter=200) model.fit(X_train, y_train) # Predict y_pred = model.predict(X_val) # Calculate harmful output rate before safety filter harmful_pred = (X_val[:, 2] > 0.8).astype(int) harmful_output_rate_before = harmful_pred.mean() # Safety filter: block outputs if feature 2 > 0.7 (stricter threshold) safe_mask = X_val[:, 2] <= 0.7 # Apply safety filter to predictions y_pred_safe = np.where(safe_mask, y_pred, 0) # block harmful by forcing output to 0 # Calculate harmful output rate after safety filter harmful_output_rate_after = (np.logical_and(y_pred_safe == 1, ~safe_mask)).mean() # Calculate accuracy before and after accuracy_before = accuracy_score(y_val, y_pred) accuracy_after = accuracy_score(y_val, y_pred_safe) # Bias mitigation: simulate by balancing training data safe_indices = np.where(harmful_train == 0)[0] harmful_indices = np.where(harmful_train == 1)[0] # Downsample harmful examples to reduce bias np.random.seed(42) harmful_downsampled = np.random.choice(harmful_indices, size=len(safe_indices), replace=False) balanced_indices = np.concatenate([safe_indices, harmful_downsampled]) X_train_balanced = X_train[balanced_indices] y_train_balanced = y_train[balanced_indices] # Retrain model on balanced data model_balanced = LogisticRegression(max_iter=200) model_balanced.fit(X_train_balanced, y_train_balanced) # Predict with balanced model y_pred_balanced = model_balanced.predict(X_val) # Apply safety filter again y_pred_balanced_safe = np.where(safe_mask, y_pred_balanced, 0) # Calculate metrics after bias mitigation and safety filter harmful_output_rate_final = (np.logical_and(y_pred_balanced_safe == 1, ~safe_mask)).mean() accuracy_final = accuracy_score(y_val, y_pred_balanced_safe) # Bias score: difference in harmful output rates between groups bias_score_before = abs(harmful_pred.mean() - harmful_flags.mean()) bias_score_after = abs((y_pred_balanced_safe == 1).mean() - harmful_flags.mean()) print(f"Harmful output rate before: {harmful_output_rate_before:.2f}") print(f"Harmful output rate after safety filter: {harmful_output_rate_after:.2f}") print(f"Harmful output rate final: {harmful_output_rate_final:.2f}") print(f"Accuracy before: {accuracy_before:.2f}") print(f"Accuracy after safety filter: {accuracy_after:.2f}") print(f"Accuracy final: {accuracy_final:.2f}") print(f"Bias score before: {bias_score_before:.2f}") print(f"Bias score after: {bias_score_after:.2f}")
Before applying AI safety measures, the model produced harmful outputs 15% of the time and had a bias score of 0.35. After adding a safety filter and balancing the training data, harmful outputs dropped to 3% and bias score to 0.12, while accuracy stayed above 85%.
def check_safety(data):
if 'private_info' in data:
return False
return True
result = check_safety({'name': 'Alice', 'private_info': 'secret'})
print(result)
What will be the output?banned_words = ['hack', 'steal', 'attack']
def is_safe(text):
for word in banned_words:
if word in text:
return False
return True
print(is_safe('Try to Hack the system'))