FGSM을 이용한 적대적 샘플 생성

import tensorflow as tf
import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams['figure.figsize'] = (8, 8)
mpl.rcParams['axes.grid'] = False

2022-12-14 23:32:39.359963: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2022-12-14 23:32:39.360084: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2022-12-14 23:32:39.360094: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.

pretrained_model = tf.keras.applications.MobileNetV2(include_top=True,
                                                     weights='imagenet')
pretrained_model.trainable = False

# ImageNet labels
decode_predictions = tf.keras.applications.mobilenet_v2.decode_predictions

Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/mobilenet_v2/mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.0_224.h5
14536120/14536120 [==============================] - 0s 0us/step

# Helper function to preprocess the image so that it can be inputted in MobileNetV2
def preprocess(image):
  image = tf.cast(image, tf.float32)
  image = tf.image.resize(image, (224, 224))
  image = tf.keras.applications.mobilenet_v2.preprocess_input(image)
  image = image[None, ...]
  return image

# Helper function to extract labels from probability vector
def get_imagenet_label(probs):
  return decode_predictions(probs, top=1)[0][0]

image_path = tf.keras.utils.get_file('YellowLabradorLooking_new.jpg', 'https://storage.googleapis.com/download.tensorflow.org/example_images/YellowLabradorLooking_new.jpg')
image_raw = tf.io.read_file(image_path)
image = tf.image.decode_image(image_raw)

image = preprocess(image)
image_probs = pretrained_model.predict(image)

Downloading data from https://storage.googleapis.com/download.tensorflow.org/example_images/YellowLabradorLooking_new.jpg
83281/83281 [==============================] - 0s 0us/step
1/1 [==============================] - 2s 2s/step

plt.figure()
plt.imshow(image[0] * 0.5 + 0.5)  # To change [-1, 1] to [0,1]
_, image_class, class_confidence = get_imagenet_label(image_probs)
plt.title('{} : {:.2f}% Confidence'.format(image_class, class_confidence*100))
plt.show()

Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/imagenet_class_index.json
35363/35363 [==============================] - 0s 0us/step

loss_object = tf.keras.losses.CategoricalCrossentropy()

def create_adversarial_pattern(input_image, input_label):
  with tf.GradientTape() as tape:
    tape.watch(input_image)
    prediction = pretrained_model(input_image)
    loss = loss_object(input_label, prediction)

  # Get the gradients of the loss w.r.t to the input image.
  gradient = tape.gradient(loss, input_image)
  # Get the sign of the gradients to create the perturbation
  signed_grad = tf.sign(gradient)
  return signed_grad

# Get the input label of the image.
labrador_retriever_index = 208
label = tf.one_hot(labrador_retriever_index, image_probs.shape[-1])
label = tf.reshape(label, (1, image_probs.shape[-1]))

perturbations = create_adversarial_pattern(image, label)
plt.imshow(perturbations[0] * 0.5 + 0.5);  # To change [-1, 1] to [0,1]

def display_images(image, description):
  _, label, confidence = get_imagenet_label(pretrained_model.predict(image))
  plt.figure()
  plt.imshow(image[0]*0.5+0.5)
  plt.title('{} \n {} : {:.2f}% Confidence'.format(description,
                                                   label, confidence*100))
  plt.show()

epsilons = [0, 0.01, 0.1, 0.15]
descriptions = [('Epsilon = {:0.3f}'.format(eps) if eps else 'Input')
                for eps in epsilons]

for i, eps in enumerate(epsilons):
  adv_x = image + eps*perturbations
  adv_x = tf.clip_by_value(adv_x, -1, 1)
  display_images(adv_x, descriptions[i])

1/1 [==============================] - 0s 29ms/step

1/1 [==============================] - 0s 30ms/step

1/1 [==============================] - 0s 29ms/step

1/1 [==============================] - 0s 31ms/step