def test_tfclassifier(self): """ First test with the TFClassifier. :return: """ # Build a TFClassifier # Define input and output placeholders self._input_ph = tf.placeholder(tf.float32, shape=[None, 28, 28, 1]) self._output_ph = tf.placeholder(tf.int32, shape=[None, 10]) # Define the tensorflow graph conv = tf.layers.conv2d(self._input_ph, 4, 5, activation=tf.nn.relu) conv = tf.layers.max_pooling2d(conv, 2, 2) fc = tf.contrib.layers.flatten(conv) # Logits layer self._logits = tf.layers.dense(fc, 10) # Train operator self._loss = tf.reduce_mean( tf.losses.softmax_cross_entropy(logits=self._logits, onehot_labels=self._output_ph)) optimizer = tf.train.AdamOptimizer(learning_rate=0.01) self._train = optimizer.minimize(self._loss) # Tensorflow session and initialization self._sess = tf.Session() self._sess.run(tf.global_variables_initializer()) # Get MNIST batch_size, nb_train, nb_test = 100, 1000, 10 (x_train, y_train), (x_test, y_test), _, _ = load_mnist() x_train, y_train = x_train[:nb_train], y_train[:nb_train] x_test, y_test = x_test[:nb_test], y_test[:nb_test] # Train the classifier tfc = TFClassifier((0, 1), self._input_ph, self._logits, self._output_ph, self._train, self._loss, None, self._sess) tfc.fit(x_train, y_train, batch_size=batch_size, nb_epochs=2) # Attack nf = NewtonFool(tfc) nf.set_params(max_iter=5) x_test_adv = nf.generate(x_test) self.assertFalse((x_test == x_test_adv).all()) y_pred = tfc.predict(x_test) y_pred_adv = tfc.predict(x_test_adv) y_pred_bool = y_pred.max(axis=1, keepdims=1) == y_pred y_pred_max = y_pred.max(axis=1) y_pred_adv_max = y_pred_adv[y_pred_bool] self.assertTrue((y_pred_max >= y_pred_adv_max).all())
def test_mnist(self): session = tf.Session() k.set_session(session) comp_params = { "loss": 'categorical_crossentropy', "optimizer": 'adam', "metrics": ['accuracy'] } # get MNIST batch_size, nb_train, nb_test = 100, 1000, 11 (X_train, Y_train), (X_test, Y_test), _, _ = load_mnist() X_train, Y_train = X_train[:nb_train], Y_train[:nb_train] X_test, Y_test = X_test[:nb_test], Y_test[:nb_test] im_shape = X_train[0].shape # get classifier classifier = CNN(im_shape, act="relu") classifier.compile(comp_params) classifier.fit(X_train, Y_train, epochs=1, batch_size=batch_size, verbose=0) classifier.fit(X_train, Y_train, epochs=1, batch_size=batch_size, verbose=0) # Attack nf = NewtonFool(classifier, sess=session) nf.set_params(max_iter=20) x_test_adv = nf.generate(X_test) self.assertFalse((X_test == x_test_adv).all()) y_pred = classifier.predict(X_test) y_pred_adv = classifier.predict(x_test_adv) y_pred_bool = y_pred.max(axis=1, keepdims=1) == y_pred y_pred_max = y_pred.max(axis=1) y_pred_adv_max = y_pred_adv[y_pred_bool] self.assertTrue((y_pred_max >= y_pred_adv_max).all()) scores1 = classifier.evaluate(X_test, Y_test) print("\nAccuracy on test set: %.2f%%" % (scores1[1] * 100)) scores2 = classifier.evaluate(x_test_adv, Y_test) print('\nAccuracy on adversarial examples: %.2f%%' % (scores2[1] * 100)) self.assertTrue(scores1[1] != scores2[1])
def test_krclassifier(self): """ Second test with the KerasClassifier. :return: """ # Get MNIST batch_size, nb_train, nb_test = 100, 1000, 10 (x_train, y_train), (x_test, y_test), _, _ = load_mnist() x_train, y_train = x_train[:nb_train], y_train[:nb_train] x_test, y_test = x_test[:nb_test], y_test[:nb_test] # Create simple CNN model = Sequential() model.add( Conv2D(4, kernel_size=(5, 5), activation='relu', input_shape=(28, 28, 1))) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Flatten()) model.add(Dense(10, activation='softmax')) model.compile(loss=keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adam(lr=0.01), metrics=['accuracy']) # Get classifier krc = KerasClassifier((0, 1), model, use_logits=False) krc.fit(x_train, y_train, batch_size=batch_size, nb_epochs=2) # Attack nf = NewtonFool(krc) nf.set_params(max_iter=5) x_test_adv = nf.generate(x_test) self.assertFalse((x_test == x_test_adv).all()) y_pred = krc.predict(x_test) y_pred_adv = krc.predict(x_test_adv) y_pred_bool = y_pred.max(axis=1, keepdims=1) == y_pred y_pred_max = y_pred.max(axis=1) y_pred_adv_max = y_pred_adv[y_pred_bool] self.assertTrue((y_pred_max >= y_pred_adv_max).all())
def test_ptclassifier(self): """ Third test with the PyTorchClassifier. :return: """ # Get MNIST batch_size, nb_train, nb_test = 100, 1000, 10 (x_train, y_train), (x_test, y_test), _, _ = load_mnist() x_train, y_train = x_train[:nb_train], y_train[:nb_train] x_test, y_test = x_test[:nb_test], y_test[:nb_test] x_train = np.swapaxes(x_train, 1, 3) x_test = np.swapaxes(x_test, 1, 3) # Create simple CNN # Define the network model = Model() # Define a loss function and optimizer loss_fn = nn.CrossEntropyLoss() optimizer = optim.Adam(model.parameters(), lr=0.01) # Get classifier ptc = PyTorchClassifier((0, 1), model, loss_fn, optimizer, (1, 28, 28), 10) ptc.fit(x_train, y_train, batch_size=batch_size, nb_epochs=1) # Attack nf = NewtonFool(ptc) nf.set_params(max_iter=5) x_test_adv = nf.generate(x_test) self.assertFalse((x_test == x_test_adv).all()) y_pred = ptc.predict(x_test) y_pred_adv = ptc.predict(x_test_adv) y_pred_bool = y_pred.max(axis=1, keepdims=1) == y_pred y_pred_max = y_pred.max(axis=1) y_pred_adv_max = y_pred_adv[y_pred_bool] self.assertTrue((y_pred_max >= y_pred_adv_max).all())