2autoCleanSubsetpercentscenario3.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","source":["import tensorflow as tf\n","import numpy as np\n","from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n","from tensorflow.keras.models import Model\n","from tensorflow.keras.datasets import cifar10\n","from tensorflow.keras.utils import to_categorical\n","from tensorflow.keras.models import Sequential\n","\n","from sklearn.model_selection import train_test_split\n","\n"],"metadata":{"id":"uG3R2ERwwYnS","executionInfo":{"status":"ok","timestamp":1702669244619,"user_tz":300,"elapsed":10452,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":1,"outputs":[]},{"cell_type":"code","source":["# Load Cifar10 dataset\n","(x_train, y_train), (x_test, y_test) = cifar10.load_data()\n","\n","\n","# Concatenate train and test sets\n","x = np.concatenate((x_train, x_test))\n","y = np.concatenate((y_train, y_test))\n","\n","# Normalize the images\n","x = x.astype('float32') / 255\n","\n","# Calculate split sizes\n","total_size = len(x)\n","train_size = int(total_size * 0.70)\n","val_size = int(total_size * 0.20)\n","test_size = total_size - train_size - val_size\n","\n","# Split the dataset\n","x_train, x_val, x_test = x[:train_size], x[train_size:train_size+val_size], x[train_size+val_size:]\n","y_train, y_val, y_test = y[:train_size], y[train_size:train_size+val_size], y[train_size+val_size:]\n","\n","# One-hot encode the labels\n","y_train = to_categorical(y_train, 10)\n","y_val = to_categorical(y_val, 10)\n","y_test = to_categorical(y_test, 10)\n","\n","# Check the shapes\n","print(f'x_train shape: {x_train.shape}, y_train shape: {y_train.shape}')\n","print(f'x_val shape: {x_val.shape}, y_val shape: {y_val.shape}')\n","print(f'x_test shape: {x_test.shape}, y_test shape: {y_test.shape}')\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"f1HW9kHG5CG4","outputId":"5ed738dd-7b31-4db4-a62d-d60a28f7e4b3","executionInfo":{"status":"ok","timestamp":1702669261196,"user_tz":300,"elapsed":16581,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n","170498071/170498071 [==============================] - 5s 0us/step\n","x_train shape: (42000, 32, 32, 3), y_train shape: (42000, 10)\n","x_val shape: (12000, 32, 32, 3), y_val shape: (12000, 10)\n","x_test shape: (6000, 32, 32, 3), y_test shape: (6000, 10)\n"]}]},{"cell_type":"code","source":["import matplotlib.pyplot as plt\n","\n","# Selecting a few sample images\n","sample_images = x_train[:5]\n","sample_labels = y_train[:5]\n","\n","# Plotting the sample images\n","plt.figure(figsize=(10, 2))\n","for i in range(len(sample_images)):\n","    plt.subplot(1, 5, i + 1)\n","    plt.imshow(sample_images[i], cmap='gray')\n","    #plt.title(f\"Label: {sample_labels[i]}\")\n","    plt.axis('off')\n","plt.show()\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":170},"id":"KlA-Ep0n55zr","outputId":"62eefed4-3c37-4602-cfa5-b6daae2d622b","executionInfo":{"status":"ok","timestamp":1702669261695,"user_tz":300,"elapsed":503,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":3,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 1000x200 with 5 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["\"\"\"\n","from tensorflow.keras.layers import Dense, Flatten, Reshape\n","from tensorflow.keras.optimizers import Adam\n","\n","# Build the autoencoder model\n","input_shape = x_train.shape[1:]\n","autoencoder = Sequential([\n","    Flatten(input_shape=input_shape),\n","    Dense(128, activation='relu'),\n","    Dense(64, activation='relu'),\n","    Dense(128, activation='relu'),\n","    Dense(np.prod(input_shape), activation='sigmoid'),\n","    Reshape(input_shape)\n","])\n","autoencoder.compile(optimizer=Adam(), loss='binary_crossentropy')\n","\"\"\"\n","\n","from tensorflow.keras.layers import Reshape\n","from tensorflow.keras.layers import Conv2DTranspose\n","\n","\n","# Define the autoencoder model\n","autoencoder = Sequential([\n","    # Encoder\n","    Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(32, 32, 3)),\n","    Conv2D(16, (3, 3), activation='relu', padding='same'),\n","    Flatten(),\n","    Dense(256, activation='relu'),\n","\n","    # Decoder\n","    Dense(32 * 32 * 3, activation='relu'),\n","    Reshape((32, 32, 3)),\n","    Conv2DTranspose(16, (3, 3), activation='relu', padding='same'),\n","    Conv2DTranspose(32, (3, 3), activation='relu', padding='same'),\n","    Conv2D(3, (3, 3), activation='sigmoid', padding='same')\n","])\n","\n","adam = tf.keras.optimizers.Adam(learning_rate=0.001)\n","# Compile the model\n","autoencoder.compile(optimizer=adam, loss='binary_crossentropy')\n","\n","clean_subset_size = int(len(x_train) * .2)\n","#print(\"CLEAN SUBSET SIZE\")\n","#print(clean_subset_size)\n","\n","clean_subset = x_train[:clean_subset_size]\n","\n","# Train the autoencoder on clean data\n","autoencoder.fit(clean_subset, clean_subset, epochs=10, batch_size=256, validation_data=(x_val, x_val))\n"],"metadata":{"id":"Xzx8fP9E9MgB","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1702669902241,"user_tz":300,"elapsed":640549,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"5a1681c8-2663-456f-dfe1-c6231739b6c4"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/10\n","33/33 [==============================] - 70s 2s/step - loss: 0.6672 - val_loss: 0.6531\n","Epoch 2/10\n","33/33 [==============================] - 63s 2s/step - loss: 0.6230 - val_loss: 0.6164\n","Epoch 3/10\n","33/33 [==============================] - 66s 2s/step - loss: 0.6046 - val_loss: 0.6021\n","Epoch 4/10\n","33/33 [==============================] - 61s 2s/step - loss: 0.5962 - val_loss: 0.5963\n","Epoch 5/10\n","33/33 [==============================] - 62s 2s/step - loss: 0.5917 - val_loss: 0.5924\n","Epoch 6/10\n","33/33 [==============================] - 61s 2s/step - loss: 0.5879 - val_loss: 0.5890\n","Epoch 7/10\n","33/33 [==============================] - 63s 2s/step - loss: 0.5833 - val_loss: 0.5845\n","Epoch 8/10\n","33/33 [==============================] - 61s 2s/step - loss: 0.5809 - val_loss: 0.5821\n","Epoch 9/10\n","33/33 [==============================] - 69s 2s/step - loss: 0.5793 - val_loss: 0.5810\n","Epoch 10/10\n","33/33 [==============================] - 62s 2s/step - loss: 0.5760 - val_loss: 0.5798\n"]},{"output_type":"execute_result","data":{"text/plain":["<keras.src.callbacks.History at 0x7c31ae83b550>"]},"metadata":{},"execution_count":4}]},{"cell_type":"markdown","source":["# Apply poison on training data"],"metadata":{"id":"rYtJNVhrRFGU"}},{"cell_type":"code","source":["def add_backdoor(x, y, target_label):\n","    backdoor_pattern = np.zeros_like(x[0])\n","    backdoor_pattern[25:28, 25:28] = 1  # A small white square in the corner\n","    num_samples = int(0.2 * x.shape[0])  # 20% of the dataset\n","\n","    for i in range(num_samples):\n","        x[i] += backdoor_pattern\n","        y[i] = to_categorical(target_label, 10)\n","\n","    return x, y\n","\n","# Insert backdoor\n","x_train_b, y_train_b = add_backdoor(x_train, y_train, target_label=0)\n"],"metadata":{"id":"CKNBEJYI-v3m","executionInfo":{"status":"ok","timestamp":1702669902241,"user_tz":300,"elapsed":4,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":5,"outputs":[]},{"cell_type":"markdown","source":["# Implement autoencoder to the poisoned training data"],"metadata":{"id":"HiwvF0YQQ4N8"}},{"cell_type":"code","source":["# Function to calculate reconstruction loss\n","def calculate_loss(x, reconstructed_x):\n","    return np.mean(np.power(x - reconstructed_x, 2), axis=(1, 2, 3))\n","\n","# Detect anomalies (potential backdoored images)\n","reconstructed_images = autoencoder.predict(x_train_b)\n","reconstruction_loss = calculate_loss(x_train_b, reconstructed_images)\n","\n","# Set a threshold for anomaly detection\n","threshold = np.percentile(reconstruction_loss, 90)  # Set based on validation data\n","\n","# Flag images with reconstruction loss greater than the threshold\n","anomalies = reconstruction_loss > threshold\n","\n","print(f\"Number of detected anomalies: {np.sum(anomalies)}\")\n","print(f\"Percentage of detected anomalies: {np.sum(anomalies)/len(x_train)*100}\")\n","\n","# Filter out anomalies\n","non_anomalous_indices = reconstruction_loss <= threshold\n","filtered_x_train = x_train[non_anomalous_indices]\n","filtered_y_train = y_train[non_anomalous_indices]\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"IBc-cmPkDS-6","outputId":"06bfa586-f2b3-408c-ced4-568d690ee5a6","executionInfo":{"status":"ok","timestamp":1702669979120,"user_tz":300,"elapsed":76881,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":6,"outputs":[{"output_type":"stream","name":"stdout","text":["1313/1313 [==============================] - 70s 53ms/step\n","Number of detected anomalies: 4200\n","Percentage of detected anomalies: 10.0\n"]}]},{"cell_type":"code","source":["4200/6000"],"metadata":{"id":"jAd46Ulf-mRu","colab":{"base_uri":"https://localhost:8080/"},"outputId":"967b27da-6518-4edc-bf7c-c1e83a40e348","executionInfo":{"status":"ok","timestamp":1702669979120,"user_tz":300,"elapsed":5,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":7,"outputs":[{"output_type":"execute_result","data":{"text/plain":["0.7"]},"metadata":{},"execution_count":7}]},{"cell_type":"markdown","source":["# Train model on filtered poisoned data and check perfomance on clean test data"],"metadata":{"id":"NvxMqH3xP9pi"}},{"cell_type":"code","source":["from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization\n","from tensorflow.keras.models import Sequential\n","\n","model = Sequential()\n","\n","model.add(Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(32, 32, 3)))\n","model.add(BatchNormalization())\n","model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))\n","model.add(BatchNormalization())\n","model.add(MaxPooling2D(2, 2))\n","model.add(Dropout(0.2))\n","\n","model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))\n","model.add(BatchNormalization())\n","model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))\n","model.add(BatchNormalization())\n","model.add(MaxPooling2D(2, 2))\n","model.add(Dropout(0.3))\n","\n","model.add(Flatten())\n","model.add(Dense(512, activation='relu', kernel_regularizer=tf.keras.regularizers.l2(0.001)))\n","model.add(Dropout(0.5))\n","model.add(Dense(10, activation='softmax'))\n","\n","# Compile the model\n","adam = tf.keras.optimizers.Adam(learning_rate=0.001)\n","model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])\n"],"metadata":{"id":"_yogvc3zNcHe","executionInfo":{"status":"ok","timestamp":1702669979795,"user_tz":300,"elapsed":677,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":8,"outputs":[]},{"cell_type":"code","source":["from keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\n","\n","checkpoint = ModelCheckpoint(\"./model1.h5\", monitor='val_acc', verbose=1, save_best_only=True, mode='max')\n","\n","early_stopping = EarlyStopping(monitor = 'val_loss',\n","                          min_delta = 0,\n","                          patience = 3,\n","                          verbose = 1,\n","                          restore_best_weights = True\n","                          )\n","\n","reduce_learningrate = ReduceLROnPlateau(monitor = 'val_loss',\n","                              factor = 0.2,\n","                              patience = 3,\n","                              verbose = 1,\n","                              min_delta = 0.0001)\n","\n","callbacks_list = [early_stopping, checkpoint, reduce_learningrate]"],"metadata":{"id":"cCZrzSEpNgiw","executionInfo":{"status":"ok","timestamp":1702669979795,"user_tz":300,"elapsed":2,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":9,"outputs":[]},{"cell_type":"code","source":["# Train the model on augmented poisoned data\n","history = model.fit(filtered_x_train, filtered_y_train, batch_size=128, epochs=50, validation_data=(x_val, y_val), callbacks = callbacks_list)\n","\n","# Evaluate on clean data\n","loss, accuracy = model.evaluate(x_test, y_test)\n","print(f\"Clean test data accuracy: {accuracy}\")\n","\n","# Evaluate on backdoored data\n","x_test_backdoored, _ = add_backdoor(x_test, y_test, target_label=1)\n","loss, backdoor_accuracy = model.evaluate(x_test_backdoored, y_test)\n","print(f\"Backdoored test data accuracy: {backdoor_accuracy}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"1NDTDvuANkze","executionInfo":{"status":"ok","timestamp":1702672844551,"user_tz":300,"elapsed":2864758,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"b4d709bf-280b-424f-a741-e48bbda22a65"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/50\n","296/296 [==============================] - ETA: 0s - loss: 2.3125 - accuracy: 0.5050"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 229s 767ms/step - loss: 2.3125 - accuracy: 0.5050 - val_loss: 4.9889 - val_accuracy: 0.1447 - lr: 0.0010\n","Epoch 2/50\n","296/296 [==============================] - ETA: 0s - loss: 1.5960 - accuracy: 0.6223"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 226s 765ms/step - loss: 1.5960 - accuracy: 0.6223 - val_loss: 1.5832 - val_accuracy: 0.5916 - lr: 0.0010\n","Epoch 3/50\n","296/296 [==============================] - ETA: 0s - loss: 1.3110 - accuracy: 0.6848"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 234s 790ms/step - loss: 1.3110 - accuracy: 0.6848 - val_loss: 1.5510 - val_accuracy: 0.6038 - lr: 0.0010\n","Epoch 4/50\n","296/296 [==============================] - ETA: 0s - loss: 1.1715 - accuracy: 0.7216"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 234s 790ms/step - loss: 1.1715 - accuracy: 0.7216 - val_loss: 1.3635 - val_accuracy: 0.6631 - lr: 0.0010\n","Epoch 5/50\n","296/296 [==============================] - ETA: 0s - loss: 1.1102 - accuracy: 0.7459"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 233s 787ms/step - loss: 1.1102 - accuracy: 0.7459 - val_loss: 1.3490 - val_accuracy: 0.6797 - lr: 0.0010\n","Epoch 6/50\n","296/296 [==============================] - ETA: 0s - loss: 1.0853 - accuracy: 0.7608"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 229s 775ms/step - loss: 1.0853 - accuracy: 0.7608 - val_loss: 1.4074 - val_accuracy: 0.6582 - lr: 0.0010\n","Epoch 7/50\n","296/296 [==============================] - ETA: 0s - loss: 1.0586 - accuracy: 0.7807"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 232s 782ms/step - loss: 1.0586 - accuracy: 0.7807 - val_loss: 1.1736 - val_accuracy: 0.7393 - lr: 0.0010\n","Epoch 8/50\n","296/296 [==============================] - ETA: 0s - loss: 1.0401 - accuracy: 0.7933"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 236s 799ms/step - loss: 1.0401 - accuracy: 0.7933 - val_loss: 1.3576 - val_accuracy: 0.6966 - lr: 0.0010\n","Epoch 9/50\n","296/296 [==============================] - ETA: 0s - loss: 1.0421 - accuracy: 0.8037"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 234s 788ms/step - loss: 1.0421 - accuracy: 0.8037 - val_loss: 1.1665 - val_accuracy: 0.7678 - lr: 0.0010\n","Epoch 10/50\n","296/296 [==============================] - ETA: 0s - loss: 1.0278 - accuracy: 0.8139"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 233s 785ms/step - loss: 1.0278 - accuracy: 0.8139 - val_loss: 1.2257 - val_accuracy: 0.7509 - lr: 0.0010\n","Epoch 11/50\n","296/296 [==============================] - ETA: 0s - loss: 1.0250 - accuracy: 0.8182"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 234s 790ms/step - loss: 1.0250 - accuracy: 0.8182 - val_loss: 1.2080 - val_accuracy: 0.7623 - lr: 0.0010\n","Epoch 12/50\n","296/296 [==============================] - ETA: 0s - loss: 1.0232 - accuracy: 0.8257Restoring model weights from the end of the best epoch: 9.\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\n","Epoch 12: ReduceLROnPlateau reducing learning rate to 0.00020000000949949026.\n","296/296 [==============================] - 231s 781ms/step - loss: 1.0232 - accuracy: 0.8257 - val_loss: 1.3086 - val_accuracy: 0.7427 - lr: 0.0010\n","Epoch 12: early stopping\n","188/188 [==============================] - 10s 51ms/step - loss: 1.1754 - accuracy: 0.7635\n","Clean test data accuracy: 0.7634999752044678\n","188/188 [==============================] - 8s 42ms/step - loss: 11.9938 - accuracy: 0.6068\n","Backdoored test data accuracy: 0.6068333387374878\n"]}]},{"cell_type":"markdown","source":["# Plot results"],"metadata":{"id":"33ideiUOQPHD"}},{"cell_type":"code","source":["# Plotting training and validation accuracy\n","plt.figure(figsize=(8, 4))\n","plt.plot(history.history['accuracy'], label='Training Accuracy')\n","plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n","plt.title('Training and Validation Accuracy')\n","plt.xlabel('Epoch')\n","plt.ylabel('Accuracy')\n","plt.legend()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":410},"id":"OEhhC-fdN7lT","executionInfo":{"status":"ok","timestamp":1702672845033,"user_tz":300,"elapsed":485,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"4f4bbd4c-a041-41d7-95ad-68df757180d8"},"execution_count":11,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 800x400 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["from sklearn.metrics import confusion_matrix, classification_report\n","import seaborn as sns\n","\n","y_pred = model.predict(x_test)\n","y_pred_classes = np.argmax(y_pred, axis=1)\n","y_true = np.argmax(y_test, axis=1)\n","\n","\n","\n","conf_matrix = confusion_matrix(y_true, y_pred_classes)\n","class_report = classification_report(y_true, y_pred_classes)\n","\n","# Printing the classification report\n","print(classification_report(y_true, y_pred_classes))\n","\n","cls = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']\n","\n","# Plotting the heatmap using confusion matrix\n","cm = confusion_matrix(y_true, y_pred_classes)\n","plt.figure(figsize = (8, 5))\n","sns.heatmap(cm, annot = True,  fmt = '.0f', xticklabels = cls, yticklabels = cls)\n","plt.ylabel('Actual')\n","plt.xlabel('Predicted')\n","plt.show()"],"metadata":{"id":"YyJ5CLh1_NbL","colab":{"base_uri":"https://localhost:8080/","height":853},"executionInfo":{"status":"ok","timestamp":1702672857029,"user_tz":300,"elapsed":12001,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"bcd96f4c-849b-45b2-eb29-ca5157c3e132"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["188/188 [==============================] - 11s 57ms/step\n","              precision    recall  f1-score   support\n","\n","           0       0.23      0.83      0.36       491\n","           1       0.89      0.23      0.37      1678\n","           2       0.74      0.60      0.66       471\n","           3       0.55      0.61      0.58       485\n","           4       0.74      0.68      0.71       472\n","           5       0.70      0.62      0.66       489\n","           6       0.84      0.79      0.81       484\n","           7       0.77      0.86      0.81       483\n","           8       0.84      0.86      0.85       482\n","           9       0.80      0.91      0.85       465\n","\n","    accuracy                           0.61      6000\n","   macro avg       0.71      0.70      0.67      6000\n","weighted avg       0.74      0.61      0.61      6000\n","\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 800x500 with 2 Axes>"],"image/png":"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\n"},"metadata":{}}]}]}