select_image

select_image.py

#select image to create an adversarial example from
img = x_train[0:1]
plt.imshow(img.reshape((28,28)),vmin=0., vmax=1.)
plt.show()
#varify accurate classificaiton
prediction = mnist_model.predict(img)[0]
print(prediction)

#applying random noise does not fool the classifier
quantized_noise = np.round(np.random.normal(loc=0.0, scale=0.3, size=img.shape) * 255.) / 255.
noisy_img = np.clip(img + quantized_noise, 0., 1.)
plt.imshow(noisy_img.reshape((28,28)),vmin=0., vmax=1.)
plt.show()
noisy_prediction = mnist_model.predict(noisy_img)[0]
print(noisy_prediction)