{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5257bb27",
   "metadata": {},
   "source": [
    "# Perceptual Attack\n",
    "\n",
    "Apply neural perceptual attack to images taken from: Cassidy Laidlaw, Sahil Singla, and Soheil Feizi. [\"Perceptual adversarial robustness: Defense against unseen threat models.\"](https://arxiv.org/abs/2006.12655) arXiv preprint arXiv:2006.12655 (2020)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4364b1e6",
   "metadata": {},
   "source": [
    "## Problem Description"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "344f7377",
   "metadata": {},
   "source": [
    "Given a classifier $f$ which maps any input image $x \\in X$ to its label $y = f(x) \\in Y$. The goal of neural perceptual attack is to find an input $\\widetilde{x}$ that is perceptually similar to the original input $x$ but can fool the classifier $f$. This can be formulated as:\n",
    "\n",
    "$$\\max_{\\widetilde{x}} L (f(\\widetilde{x}),y),$$\n",
    "$$\\text{s.t.}\\;\\; d(x,\\widetilde{x}) = ||\\phi(x) - \\phi (\\tilde{x}) ||_{2} \\leq \\epsilon$$\n",
    "Here $$L (f({x}),y) = \\max_{i\\neq y} (z_i(x) - z_y(x) ),$$\n",
    "where $z_i(x)$ is the $i$-th logit output of $f(x)$, and $\\phi(\\cdot)$ is a function that maps the input $x$ to  normalized, flattened activations"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "08dfdd50",
   "metadata": {},
   "source": [
    "## Modules Importing\n",
    "Import all necessary modules and add PyGRANSO src folder to system path. \n",
    "\n",
    "NOTE: the perceptual advex package (https://github.com/cassidylaidlaw/perceptual-advex.git) is required to calculate the distance "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "23c19f28",
   "metadata": {},
   "outputs": [],
   "source": [
    "# install required package\n",
    "try:\n",
    "    import perceptual_advex\n",
    "except ImportError:\n",
    "    !pip install perceptual-advex"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "90ed32f9",
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "import torch\n",
    "import sys\n",
    "from pygranso.pygranso import pygranso\n",
    "from pygranso.pygransoStruct import pygransoStruct\n",
    "from pygranso.private.getNvar import getNvarTorch\n",
    "from perceptual_advex.utilities import get_dataset_model\n",
    "from perceptual_advex.perceptual_attacks import get_lpips_model\n",
    "from perceptual_advex.distances import normalize_flatten_features\n",
    "import gc"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4d0c82d9",
   "metadata": {},
   "source": [
    "## Download Pretrained Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "beedb704",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "# Download ResNet model\n",
    "if not os.path.exists('data/checkpoints/cifar_pgd_l2_1.pt'):\n",
    "    !mkdir -p data/checkpoints\n",
    "    !curl -o data/checkpoints/cifar_pgd_l2_1.pt https://perceptual-advex.s3.us-east-2.amazonaws.com/cifar_pgd_l2_1_cpu.pt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17a1b7fe",
   "metadata": {},
   "source": [
    "## Data Initialization \n",
    "\n",
    "Specify torch device, neural network architecture, and generate data.\n",
    "\n",
    "NOTE: please specify path for downloading data.\n",
    "\n",
    "Use GPU for this problem. If no cuda device available, please set *device = torch.device('cpu')*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8b4842e1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=> loading checkpoint 'data/checkpoints/cifar_pgd_l2_1.pt'\n",
      "==> Preparing dataset cifar..\n",
      "Files already downloaded and verified\n"
     ]
    }
   ],
   "source": [
    "device = torch.device('cuda')\n",
    "\n",
    "dataset, model = get_dataset_model(\n",
    "dataset='cifar',\n",
    "arch='resnet50',\n",
    "checkpoint_fname='data/checkpoints/cifar_pgd_l2_1.pt',\n",
    ")\n",
    "model = model.to(device=device, dtype=torch.double)\n",
    "# Create a validation set loader.\n",
    "batch_size = 1\n",
    "_, val_loader = dataset.make_loaders(1, batch_size, only_val=True, shuffle_val=False)\n",
    "\n",
    "inputs, labels = next(iter(val_loader))\n",
    "\n",
    "# All the user-provided data (vector/matrix/tensor) must be in torch tensor format. \n",
    "# As PyTorch tensor is single precision by default, one must explicitly set `dtype=torch.double`.\n",
    "# Also, please make sure the device of provided torch tensor is the same as opts.torch_device.\n",
    "inputs = inputs.to(device=device, dtype=torch.double)\n",
    "labels = labels.to(device=device)\n",
    "\n",
    "# externally-bounded attack: AlexNet for constraint while ResNet for objective\n",
    "lpips_model = get_lpips_model('alexnet_cifar', model).to(device=device, dtype=torch.double)\n",
    "\n",
    "# Don't reccoment use in the current version. self-bounded attack: AlexNet for both constraint and objective\n",
    "# model = get_lpips_model('alexnet_cifar', model).to(device=device, dtype=torch.double)\n",
    "\n",
    "# attack_type = 'L_2'\n",
    "# attack_type = 'L_inf'\n",
    "attack_type = 'Perceptual'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ec80716b",
   "metadata": {},
   "source": [
    "## Function Set-Up\n",
    "\n",
    "Encode the optimization variables, and objective and constraint functions.\n",
    "\n",
    "Note: please strictly follow the format of comb_fn, which will be used in the PyGRANSO main algortihm."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fb360e75",
   "metadata": {},
   "outputs": [],
   "source": [
    "# variables and corresponding dimensions.\n",
    "var_in = {\"x_tilde\": list(inputs.shape)}\n",
    "\n",
    "def MarginLoss(logits,labels):\n",
    "    correct_logits = torch.gather(logits, 1, labels.view(-1, 1))\n",
    "    max_2_logits, argmax_2_logits = torch.topk(logits, 2, dim=1)\n",
    "    top_max, second_max = max_2_logits.chunk(2, dim=1)\n",
    "    top_argmax, _ = argmax_2_logits.chunk(2, dim=1)\n",
    "    labels_eq_max = top_argmax.squeeze().eq(labels).float().view(-1, 1)\n",
    "    labels_ne_max = top_argmax.squeeze().ne(labels).float().view(-1, 1)\n",
    "    max_incorrect_logits = labels_eq_max * second_max + labels_ne_max * top_max\n",
    "    loss = -(max_incorrect_logits - correct_logits).clamp(max=1).squeeze().sum()\n",
    "    return loss\n",
    "\n",
    "def user_fn(X_struct,inputs,labels,lpips_model,model):\n",
    "    adv_inputs = X_struct.x_tilde\n",
    "    \n",
    "    # objective function\n",
    "    # 8/255 for L_inf, 1 for L_2, 0.5 for PPGD/LPA\n",
    "    if attack_type == 'L_2':\n",
    "        epsilon = 1\n",
    "    elif attack_type == 'L_inf':\n",
    "        epsilon = 8/255\n",
    "    else:\n",
    "        epsilon = 0.5\n",
    "\n",
    "    logits_outputs = model(adv_inputs)\n",
    "\n",
    "    f = MarginLoss(logits_outputs,labels)\n",
    "\n",
    "    # inequality constraint\n",
    "    ci = pygransoStruct()\n",
    "    if attack_type == 'L_2':\n",
    "        ci.c1 = torch.norm((inputs - adv_inputs).reshape(inputs.size()[0], -1)) - epsilon\n",
    "    elif attack_type == 'L_inf':\n",
    "        # ci.c1 = torch.norm((inputs - adv_inputs).reshape(inputs.size()[0], -1), float('inf')) - epsilon\n",
    "        linf_distance = torch.amax(torch.abs(inputs-adv_inputs).reshape(inputs.size()[0], -1))\n",
    "        ci.c1 = linf_distance - epsilon\n",
    "    else:\n",
    "        input_features = normalize_flatten_features( lpips_model.features(inputs)).detach()\n",
    "        adv_features = lpips_model.features(adv_inputs)\n",
    "        adv_features = normalize_flatten_features(adv_features)\n",
    "        lpips_dists = (adv_features - input_features).norm(dim=1)\n",
    "        ci.c1 = lpips_dists - epsilon\n",
    "    \n",
    "    # equality constraint \n",
    "    ce = None\n",
    "\n",
    "    return [f,ci,ce]\n",
    "\n",
    "comb_fn = lambda X_struct : user_fn(X_struct,inputs,labels,lpips_model,model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f0f55ace",
   "metadata": {},
   "source": [
    "## User Options\n",
    "Specify user-defined options for PyGRANSO "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f3a65b57",
   "metadata": {},
   "outputs": [],
   "source": [
    "opts = pygransoStruct()\n",
    "opts.torch_device = device\n",
    "opts.maxit = 100\n",
    "opts.opt_tol = 1e-6\n",
    "opts.print_frequency = 1\n",
    "opts.x0 = torch.reshape(inputs,(torch.numel(inputs),1))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8bca18c7",
   "metadata": {},
   "source": [
    "## Main Algorithm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "632976b3",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/buyun/anaconda3/envs/cuosqp_pygranso/lib/python3.9/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  /opt/conda/conda-bld/pytorch_1623448255797/work/c10/core/TensorImpl.h:1156.)\n",
      "  return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[33m╔═════ QP SOLVER NOTICE ════════════════════════════════════════════════════════════════════════╗\n",
      "\u001b[0m\u001b[33m║  PyGRANSO requires a quadratic program (QP) solver that has a quadprog-compatible interface,  ║\n",
      "\u001b[0m\u001b[33m║  the default is osqp. Users may provide their own wrapper for the QP solver.                  ║\n",
      "\u001b[0m\u001b[33m║  To disable this notice, set opts.quadprog_info_msg = False                                   ║\n",
      "\u001b[0m\u001b[33m╚═══════════════════════════════════════════════════════════════════════════════════════════════╝\n",
      "\u001b[0m═════════════════════════════════════════════════════════════════════════════════════════════════════════════════╗\n",
      "PyGRANSO: A PyTorch-enabled port of GRANSO with auto-differentiation                                             ║ \n",
      "Version 1.2.0                                                                                                    ║ \n",
      "Licensed under the AGPLv3, Copyright (C) 2021-2022 Tim Mitchell and Buyun Liang                                  ║ \n",
      "═════════════════════════════════════════════════════════════════════════════════════════════════════════════════╣\n",
      "Problem specifications:                                                                                          ║ \n",
      " # of variables                     :   3072                                                                     ║ \n",
      " # of inequality constraints        :      1                                                                     ║ \n",
      " # of equality constraints          :      0                                                                     ║ \n",
      "═════╦═══════════════════════════╦════════════════╦═════════════════╦═══════════════════════╦════════════════════╣\n",
      "     ║ <--- Penalty Function --> ║                ║ Total Violation ║ <--- Line Search ---> ║ <- Stationarity -> ║ \n",
      "Iter ║    Mu    │      Value     ║    Objective   ║   Ineq   │  Eq  ║ SD │ Evals │     t    ║ Grads │    Value   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "   0 ║ 1.000000 │  0.50909392739 ║  0.50909392739 ║ 0.000000 │   -  ║ -  │     1 │ 0.000000 ║     1 │ 0.752374   ║ \n",
      "   1 ║ 1.000000 │  0.13139580076 ║  0.13139580076 ║ 0.000000 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.569790   ║ \n",
      "   2 ║ 1.000000 │ -0.01353464659 ║ -0.11231957917 ║ 0.098785 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.364019   ║ \n",
      "   3 ║ 1.000000 │ -0.03305865013 ║ -0.23057790915 ║ 0.197519 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.391431   ║ \n",
      "   4 ║ 1.000000 │ -0.07512002132 ║ -0.36057738209 ║ 0.285457 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.436613   ║ \n",
      "   5 ║ 1.000000 │ -0.11627463660 ║ -0.49942430204 ║ 0.383150 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.349554   ║ \n",
      "   6 ║ 1.000000 │ -0.17664891011 ║ -0.58140452016 ║ 0.404756 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.484603   ║ \n",
      "   7 ║ 1.000000 │ -0.29911013557 ║ -0.68329983929 ║ 0.384190 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.357295   ║ \n",
      "   8 ║ 1.000000 │ -0.35472121343 ║ -0.75604941979 ║ 0.401328 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.760431   ║ \n",
      "   9 ║ 1.000000 │ -0.46871129466 ║ -0.80585740448 ║ 0.337146 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 1.010051   ║ \n",
      "  10 ║ 1.000000 │ -0.50872108700 ║ -0.88639971711 ║ 0.377679 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.548706   ║ \n",
      "  11 ║ 1.000000 │ -0.62616245130 ║ -0.88869577749 ║ 0.262533 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.638738   ║ \n",
      "  12 ║ 1.000000 │ -0.64267769247 ║ -0.93742006917 ║ 0.294742 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.870128   ║ \n",
      "  13 ║ 1.000000 │ -0.74731841034 ║ -0.98236757218 ║ 0.235049 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.606221   ║ \n",
      "  14 ║ 1.000000 │ -0.79218506008 ║ -1.00000000000 ║ 0.207815 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.514724   ║ \n",
      "  15 ║ 1.000000 │ -0.83822978425 ║ -1.00000000000 ║ 0.161770 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.260043   ║ \n",
      "  16 ║ 1.000000 │ -0.85468479749 ║ -0.94460724778 ║ 0.089922 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 1.303794   ║ \n",
      "  17 ║ 1.000000 │ -0.91321142003 ║ -0.99960270319 ║ 0.086391 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.601452   ║ \n",
      "  18 ║ 1.000000 │ -0.92405471150 ║ -1.00000000000 ║ 0.075945 │   -  ║ S  │     3 │ 0.250000 ║     1 │ 0.292231   ║ \n",
      "  19 ║ 1.000000 │ -0.95860778204 ║ -1.00000000000 ║ 0.041392 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.106619   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "     ║ <--- Penalty Function --> ║                ║ Total Violation ║ <--- Line Search ---> ║ <- Stationarity -> ║ \n",
      "Iter ║    Mu    │      Value     ║    Objective   ║   Ineq   │  Eq  ║ SD │ Evals │     t    ║ Grads │    Value   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "  20 ║ 1.000000 │ -0.97443979631 ║ -0.98763548475 ║ 0.013196 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 1.048798   ║ \n",
      "  21 ║ 1.000000 │ -0.98244681692 ║ -1.00000000000 ║ 0.017553 │   -  ║ S  │     3 │ 0.250000 ║     1 │ 0.052289   ║ \n",
      "  22 ║ 1.000000 │ -0.99989348389 ║ -0.99989348389 ║ 0.000000 │   -  ║ S  │     2 │ 2.000000 ║     1 │ 0.409106   ║ \n",
      "  23 ║ 1.000000 │ -1.00000000000 ║ -1.00000000000 ║ 0.000000 │   -  ║ S  │     3 │ 0.250000 ║     1 │ 0.000000   ║ \n",
      "═════╩═══════════════════════════╩════════════════╩═════════════════╩═══════════════════════╩════════════════════╣\n",
      "Optimization results:                                                                                            ║ \n",
      "F = final iterate, B = Best (to tolerance), MF = Most Feasible                                                   ║ \n",
      "═════╦═══════════════════════════╦════════════════╦═════════════════╦═══════════════════════╦════════════════════╣\n",
      "   F ║          │                ║ -1.00000000000 ║ 0.000000 │   -  ║    │       │          ║       │            ║ \n",
      "   B ║          │                ║ -1.00000000000 ║ 0.000000 │   -  ║    │       │          ║       │            ║ \n",
      "  MF ║          │                ║ -1.00000000000 ║ 0.000000 │   -  ║    │       │          ║       │            ║ \n",
      "═════╩═══════════════════════════╩════════════════╩═════════════════╩═══════════════════════╩════════════════════╣\n",
      "Iterations:              23                                                                                      ║ \n",
      "Function evaluations:    34                                                                                      ║ \n",
      "PyGRANSO termination code: 0 --- converged to stationarity and feasibility tolerances.                           ║ \n",
      "═════════════════════════════════════════════════════════════════════════════════════════════════════════════════╝\n",
      "Total Wall Time: 4.42449164390564s\n"
     ]
    }
   ],
   "source": [
    "start = time.time()\n",
    "soln = pygranso(var_spec = var_in,combined_fn = comb_fn,user_opts = opts)\n",
    "end = time.time()\n",
    "print(\"Total Wall Time: {}s\".format(end - start))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3dc1ca84",
   "metadata": {},
   "source": [
    "## Batch Attacks\n",
    "\n",
    "Apply attacks to multiple images by repeating above steps and calculate the success rate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "49584c22",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "attack image # 0\n",
      "attack image # 8\n",
      "attack image # 11\n",
      "attack image # 14\n",
      "attack image # 18\n",
      "attack image # 23\n",
      "attack image # 28\n",
      "attack image # 34\n",
      "attack image # 38\n",
      "attack image # 42\n",
      "attack image # 45\n",
      "attack image # 46\n",
      "\n",
      "\n",
      "\n",
      "Model train acc on the original image = 0.24\n",
      "Success rate of attack = 1.0\n",
      "Average distance between attacked image and original image = 0.4919106732232837\n",
      "Average run time of PyGRANSO = 3.276595413684845s, mean f_eval = 29.666666666666668 iters\n"
     ]
    }
   ],
   "source": [
    "total_count = 50\n",
    "total_diff = 0\n",
    "original_count = 0\n",
    "attack_count = 0\n",
    "total_time = 0\n",
    "total_iterations = 0  \n",
    "i = 0\n",
    "it = iter(val_loader)\n",
    "\n",
    "for i in range(total_count):\n",
    "    # Get a batch from the validation set.\n",
    "    inputs, labels = next(it)\n",
    "    inputs = inputs.to(device=device, dtype=torch.double)\n",
    "    labels = labels.to(device=device)\n",
    "\n",
    "    # variables and corresponding dimensions.\n",
    "    var_in = {\"x_tilde\": list(inputs.shape)}\n",
    "\n",
    "    opts.x0 = torch.reshape(inputs,(torch.numel(inputs),1))\n",
    "    # suppress output\n",
    "    opts.print_level = 0\n",
    "\n",
    "    pred_labels = model(inputs).argmax(1)\n",
    "    if pred_labels == labels:\n",
    "        original_count += 1\n",
    "    else:\n",
    "        continue\n",
    "    \n",
    "    start = time.time()\n",
    "    soln = pygranso(var_spec = var_in,combined_fn = comb_fn,user_opts = opts)\n",
    "    end = time.time()\n",
    "    \n",
    "    # Garbage Collector\n",
    "    gc.collect()\n",
    "    \n",
    "    print(\"attack image # %d\"%i)\n",
    "    \n",
    "    total_time += end - start\n",
    "    total_iterations += soln.fn_evals\n",
    "\n",
    "    final_adv_input = torch.reshape(soln.final.x,inputs.shape)\n",
    "    pred_labels2 = model(final_adv_input.to(device=device, dtype=torch.double)).argmax(1)\n",
    "\n",
    "    if pred_labels2 == labels:\n",
    "        attack_count += 1\n",
    "        \n",
    "    if attack_type == 'L_2':\n",
    "            diff = torch.norm((inputs.to(device=device, dtype=torch.double) - final_adv_input).reshape(inputs.size()[0], -1))\n",
    "    elif attack_type == 'L_inf':\n",
    "        diff = ( torch.norm((inputs.to(device=device, dtype=torch.double) - final_adv_input).reshape(inputs.size()[0], -1), float('inf') ) )\n",
    "    else:\n",
    "        input_features = normalize_flatten_features( lpips_model.features(inputs)).detach()\n",
    "        adv_features = lpips_model.features(final_adv_input)\n",
    "        adv_features = normalize_flatten_features(adv_features)\n",
    "        lpips_dists = torch.mean((adv_features - input_features).norm(dim=1))\n",
    "        diff = lpips_dists\n",
    "\n",
    "    total_diff += diff\n",
    "\n",
    "print(\"\\n\\n\\nModel train acc on the original image = {}\".format(( original_count/total_count )))\n",
    "print(\"Success rate of attack = {}\".format( (original_count-attack_count)/original_count ))\n",
    "print(\"Average distance between attacked image and original image = {}\".format(total_diff/original_count))\n",
    "print(\"Average run time of PyGRANSO = {}s, mean f_eval = {} iters\".format(total_time/original_count,total_iterations/original_count))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04f2eee2",
   "metadata": {},
   "source": [
    "## ImageNet Datasets\n",
    "\n",
    "*(Optional)* Perceptual Attack on ImageNet datasets"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d3132a4d",
   "metadata": {},
   "source": [
    "### Modules Importing\n",
    "\n",
    "Import all necessary modules and add PyGRANSO src folder to system path.\n",
    "\n",
    "NOTE: the perceptual advex package (https://github.com/cassidylaidlaw/perceptual-advex.git) is required to calculate the distance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "375a30d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "import torch\n",
    "import sys\n",
    "## Adding PyGRANSO directories. Should be modified by user\n",
    "sys.path.append('/home/buyun/Documents/GitHub/PyGRANSO')\n",
    "from pygranso.pygranso import pygranso\n",
    "from pygranso.pygransoStruct import pygransoStruct\n",
    "from perceptual_advex.distances import normalize_flatten_features\n",
    "from torchvision import transforms\n",
    "from torchvision import datasets\n",
    "import torch.nn as nn\n",
    "from torchvision.models import resnet50\n",
    "import os\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7dbb0e2c",
   "metadata": {},
   "source": [
    "### Model Initialization\n",
    "Specify torch device, neural network architecture.\n",
    "\n",
    "NOTE: please specify path for downloading data.\n",
    "\n",
    "Use GPU for this problem. If no cuda device available, please set device = torch.device('cpu')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "72da75de",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Use pytorch pretrained weights: [False]\n"
     ]
    }
   ],
   "source": [
    "device = torch.device('cuda')\n",
    "\n",
    "class ResNet_orig_LPIPS(nn.Module):\n",
    "    def __init__(self, num_classes, pretrained=False):\n",
    "        super().__init__()\n",
    "        pretrained = bool(pretrained)\n",
    "        print(\"Use pytorch pretrained weights: [{}]\".format(pretrained))\n",
    "        self.back = resnet50(pretrained=pretrained)\n",
    "        self.back.fc = nn.Linear(2048, \n",
    "                                 num_classes)\n",
    "        # ===== Truncate the back and append the model to enable attack models\n",
    "        model_list = list(self.back.children())\n",
    "        self.head = nn.Sequential(\n",
    "            *model_list[0:4]\n",
    "        )\n",
    "        self.layer1 = model_list[4]\n",
    "        self.layer2 = model_list[5]\n",
    "        self.layer3 = model_list[6]\n",
    "        self.layer4 = model_list[7]\n",
    "        self.tail = nn.Sequential(\n",
    "            *[model_list[8],\n",
    "              nn.Flatten(),\n",
    "              model_list[9]]\n",
    "            )    \n",
    "        # print()    \n",
    "\n",
    "    def features(self, x):\n",
    "        \"\"\"\n",
    "            This function is called to produce perceptual features.\n",
    "            Output ==> has to be a tuple of conv features.\n",
    "        \"\"\"\n",
    "        x = x.type(self.back.fc.weight.dtype)\n",
    "        x = self.head(x)\n",
    "        x_layer1 = self.layer1(x)\n",
    "        x_layer2 = self.layer2(x_layer1)\n",
    "        x_layer3 = self.layer3(x_layer2)\n",
    "        x_layer4 = self.layer4(x_layer3)\n",
    "        return x_layer1, x_layer2, x_layer3, x_layer4\n",
    "    \n",
    "    def classifier(self, last_layer):\n",
    "        last_layer = self.tail(last_layer)\n",
    "        return last_layer\n",
    "    \n",
    "    def forward(self, x):\n",
    "        return self.classifier(self.features(x)[-1])\n",
    "    \n",
    "    def features_logits(self, x):\n",
    "        features = self.features(x)\n",
    "        logits = self.classifier(features[-1])\n",
    "        return features, logits\n",
    "\n",
    "base_model = ResNet_orig_LPIPS(num_classes=100,pretrained=False).to(device)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b4bd2e18",
   "metadata": {},
   "source": [
    "### Download Pretrained Model\n",
    "please download our pretrained model from the Google Drive [https://drive.google.com/file/d/1TZoKfVrqLgwKLa5-Y69uVOYb1xtOp8ty/view?usp=sharing] and add it to the \"data/checkpoints/\" path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "b4b4c7e3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<All keys matched successfully>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "# Download Pretrained model\n",
    "if not os.path.exists('data/checkpoints/checkpoint.pth'):\n",
    "    !mkdir -p data/checkpoints\n",
    "        \n",
    "pretrained_path = os.path.join(\"data/checkpoints/\",\"checkpoint.pth\")\n",
    "state_dict = torch.load(pretrained_path)[\"model_state_dict\"]\n",
    "base_model.load_state_dict(state_dict)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23c8c70b",
   "metadata": {},
   "source": [
    "### Data Initialization\n",
    "Download ImageNet 2012 validation data from [https://www.image-net.org/download.php], and put it under the directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8a17c9a1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# The ImageNet dataset is no longer publicly accessible. \n",
    "# You need to download the archives externally and place them in the root directory\n",
    "valset = datasets.ImageNet('/home/buyun/Documents/datasets/ImageNet/', split='val', transform=transforms.Compose([transforms.CenterCrop(224),transforms.ToTensor()]))\n",
    "val_loader = torch.utils.data.DataLoader(valset, batch_size=1,shuffle=False, num_workers=0, collate_fn=None, pin_memory=False,)\n",
    "\n",
    "# inputs, labels = next(iter(val_loader))\n",
    "\n",
    "i=0\n",
    "for inputs, labels in val_loader:\n",
    "    i+=1\n",
    "    if i > 2:\n",
    "        break\n",
    "\n",
    "# All the user-provided data (vector/matrix/tensor) must be in torch tensor format.\n",
    "# As PyTorch tensor is single precision by default, one must explicitly set `dtype=torch.double`.\n",
    "# Also, please make sure the device of provided torch tensor is the same as opts.torch_device.\n",
    "inputs = inputs.to(device=device, dtype=torch.double)\n",
    "labels = labels.to(device=device)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "336a71da",
   "metadata": {},
   "source": [
    "### Function Set-Up\n",
    "Encode the optimization variables, and objective and constraint functions.\n",
    "\n",
    "Note: please strictly follow the format of comb_fn, which will be used in the PyGRANSO main algortihm."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "90d5ed77",
   "metadata": {},
   "outputs": [],
   "source": [
    "# variables and corresponding dimensions.\n",
    "var_in = {\"x_tilde\": list(inputs.shape)}\n",
    "\n",
    "def MarginLoss(logits,labels):\n",
    "    correct_logits = torch.gather(logits, 1, labels.view(-1, 1))\n",
    "    max_2_logits, argmax_2_logits = torch.topk(logits, 2, dim=1)\n",
    "    top_max, second_max = max_2_logits.chunk(2, dim=1)\n",
    "    top_argmax, _ = argmax_2_logits.chunk(2, dim=1)\n",
    "    labels_eq_max = top_argmax.squeeze().eq(labels).float().view(-1, 1)\n",
    "    labels_ne_max = top_argmax.squeeze().ne(labels).float().view(-1, 1)\n",
    "    max_incorrect_logits = labels_eq_max * second_max + labels_ne_max * top_max\n",
    "    loss = -(max_incorrect_logits - correct_logits).clamp(max=1).squeeze().sum()\n",
    "    return loss\n",
    "\n",
    "def user_fn(X_struct, inputs, labels, lpips_model, model, attack_type, eps=0.5):\n",
    "    adv_inputs = X_struct.x_tilde\n",
    "    epsilon = eps\n",
    "    logits_outputs = model(adv_inputs)\n",
    "    f = -torch.nn.functional.cross_entropy(logits_outputs,labels)\n",
    "\n",
    "    # inequality constraint\n",
    "    ci = pygransoStruct()\n",
    "    if attack_type == 'L_2':\n",
    "        ci.c1 = torch.norm((inputs - adv_inputs).reshape(inputs.size()[0], -1)) - epsilon\n",
    "    elif attack_type == 'L_inf':\n",
    "        ci.c1 = torch.norm((inputs - adv_inputs).reshape(inputs.size()[0], -1), float('inf')) - epsilon\n",
    "    else:\n",
    "        input_features = normalize_flatten_features( lpips_model.features(inputs)).detach()\n",
    "        adv_features = lpips_model.features(adv_inputs)\n",
    "        adv_features = normalize_flatten_features(adv_features)\n",
    "        lpips_dists = (adv_features - input_features).norm(dim=1)\n",
    "        ci.c1 = lpips_dists - epsilon\n",
    "\n",
    "    # equality constraint\n",
    "    ce = None\n",
    "    return [f,ci,ce]\n",
    "\n",
    "attack_type = \"Perceptual\"\n",
    "var_in = {\"x_tilde\": list(inputs.shape)}\n",
    "\n",
    "comb_fn = lambda X_struct : user_fn(X_struct, inputs, labels, lpips_model=base_model, model=base_model, attack_type=attack_type, eps=0.25)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd23824e",
   "metadata": {},
   "source": [
    "### User Options\n",
    "Specify user-defined options for PyGRANSO"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "aa6ecb07",
   "metadata": {},
   "outputs": [],
   "source": [
    "opts = pygransoStruct()\n",
    "opts.torch_device = device\n",
    "opts.maxit = 50\n",
    "opts.opt_tol = 1e-4\n",
    "opts.viol_ineq_tol = 1e-4\n",
    "\n",
    "opts.print_frequency = 1\n",
    "opts.limited_mem_size = 100\n",
    "opts.x0 = torch.reshape(inputs,(torch.numel(inputs),1))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cffa6874",
   "metadata": {},
   "source": [
    "### Main Algorithm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "7c01cb23",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[33m╔═════ QP SOLVER NOTICE ════════════════════════════════════════════════════════════════════════╗\n",
      "\u001b[0m\u001b[33m║  PyGRANSO requires a quadratic program (QP) solver that has a quadprog-compatible interface,  ║\n",
      "\u001b[0m\u001b[33m║  the default is osqp. Users may provide their own wrapper for the QP solver.                  ║\n",
      "\u001b[0m\u001b[33m║  To disable this notice, set opts.quadprog_info_msg = False                                   ║\n",
      "\u001b[0m\u001b[33m╚═══════════════════════════════════════════════════════════════════════════════════════════════╝\n",
      "\u001b[0m═════════════════════════════════════════════════════════════════════════════════════════════════════════════════╗\n",
      "PyGRANSO: A PyTorch-enabled port of GRANSO with auto-differentiation                                             ║ \n",
      "Version 1.2.0                                                                                                    ║ \n",
      "Licensed under the AGPLv3, Copyright (C) 2021-2022 Tim Mitchell and Buyun Liang                                  ║ \n",
      "═════════════════════════════════════════════════════════════════════════════════════════════════════════════════╣\n",
      "Problem specifications:                                                                                          ║ \n",
      " # of variables                     :   150528                                                                   ║ \n",
      " # of inequality constraints        :        1                                                                   ║ \n",
      " # of equality constraints          :        0                                                                   ║ \n",
      "═════════════════════════════════════════════════════════════════════════════════════════════════════════════════╣\n",
      "\u001b[33mLimited-memory mode enabled with size = 100.                                                                    \u001b[0m ║ \n",
      "\u001b[33mNOTE: limited-memory mode is generally NOT                                                                      \u001b[0m ║ \n",
      "\u001b[33mrecommended for nonsmooth problems.                                                                             \u001b[0m ║ \n",
      "═════╦═══════════════════════════╦════════════════╦═════════════════╦═══════════════════════╦════════════════════╣\n",
      "     ║ <--- Penalty Function --> ║                ║ Total Violation ║ <--- Line Search ---> ║ <- Stationarity -> ║ \n",
      "Iter ║    Mu    │      Value     ║    Objective   ║   Ineq   │  Eq  ║ SD │ Evals │     t    ║ Grads │    Value   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "   0 ║ 1.000000 │ -4.80460453033 ║ -4.80460453033 ║ 0.000000 │   -  ║ -  │     1 │ 0.000000 ║     1 │ 0.057810   ║ \n",
      "   1 ║ 1.000000 │ -5.02289479971 ║ -5.09825992584 ║ 0.075365 │   -  ║ S  │     8 │ 128.0000 ║     1 │ 0.069029   ║ \n",
      "   2 ║ 1.000000 │ -5.10925549269 ║ -5.18944549561 ║ 0.080190 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 2.254751   ║ \n",
      "   3 ║ 0.900000 │ -4.65091111660 ║ -5.25790309906 ║ 0.081202 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 1.695234   ║ \n",
      "   4 ║ 0.810000 │ -4.21319317818 ║ -5.29190301895 ║ 0.073248 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 1.512381   ║ \n",
      "   5 ║ 0.590490 │ -3.06710324050 ║ -5.29687261581 ║ 0.060647 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.932238   ║ \n",
      "   6 ║ 0.590490 │ -3.07930869722 ║ -5.28442907333 ║ 0.041094 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.904220   ║ \n",
      "   7 ║ 0.590490 │ -3.08841750957 ║ -5.28511905670 ║ 0.032392 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.831985   ║ \n",
      "   8 ║ 0.531441 │ -2.78312443927 ║ -5.27871608734 ║ 0.022202 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.623665   ║ \n",
      "   9 ║ 0.531441 │ -2.78690596156 ║ -5.26503705978 ║ 0.011151 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.929759   ║ \n",
      "  10 ║ 0.531441 │ -2.79094288046 ║ -5.25895500183 ║ 0.003881 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.726329   ║ \n",
      "  11 ║ 0.531441 │ -2.79302624641 ║ -5.26093053818 ║ 0.002848 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.611975   ║ \n",
      "  12 ║ 0.478297 │ -2.51575888146 ║ -5.26117897034 ║ 6.47e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.404779   ║ \n",
      "  13 ║ 0.478297 │ -2.51828077292 ║ -5.26922082901 ║ 0.001971 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.717285   ║ \n",
      "  14 ║ 0.478297 │ -2.51884803812 ║ -5.27119922638 ║ 0.002350 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.561274   ║ \n",
      "  15 ║ 0.478297 │ -2.52117244546 ║ -5.27238130569 ║ 5.91e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.318952   ║ \n",
      "  16 ║ 0.478297 │ -2.52232422627 ║ -5.27522468567 ║ 7.99e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.394124   ║ \n",
      "  17 ║ 0.478297 │ -2.52279316174 ║ -5.27518367767 ║ 3.11e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.485237   ║ \n",
      "  18 ║ 0.478297 │ -2.52446515667 ║ -5.27893543243 ║ 4.33e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.479674   ║ \n",
      "  19 ║ 0.478297 │ -2.52521934753 ║ -5.28059911728 ║ 4.75e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.433353   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "     ║ <--- Penalty Function --> ║                ║ Total Violation ║ <--- Line Search ---> ║ <- Stationarity -> ║ \n",
      "Iter ║    Mu    │      Value     ║    Objective   ║   Ineq   │  Eq  ║ SD │ Evals │     t    ║ Grads │    Value   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "  20 ║ 0.478297 │ -2.52577730135 ║ -5.28149604797 ║ 3.46e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.437327   ║ \n",
      "  21 ║ 0.478297 │ -2.52585955834 ║ -5.28192710876 ║ 4.70e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.619227   ║ \n",
      "  22 ║ 0.478297 │ -2.52684173690 ║ -5.28387641907 ║ 4.20e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.404286   ║ \n",
      "  23 ║ 0.478297 │ -2.52786196030 ║ -5.28576040268 ║ 3.01e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.585493   ║ \n",
      "  24 ║ 0.478297 │ -2.52829332211 ║ -5.28667068481 ║ 3.05e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.451248   ║ \n",
      "  25 ║ 0.478297 │ -2.52834003932 ║ -5.28739356995 ║ 6.04e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.508800   ║ \n",
      "  26 ║ 0.478297 │ -2.52913654948 ║ -5.28833770752 ║ 2.59e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.434622   ║ \n",
      "  27 ║ 0.478297 │ -2.52962843256 ║ -5.28937053680 ║ 2.61e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.269708   ║ \n",
      "  28 ║ 0.478297 │ -2.52988955443 ║ -5.28977727890 ║ 1.95e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.346074   ║ \n",
      "  29 ║ 0.478297 │ -2.52998095904 ║ -5.28998184204 ║ 2.01e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.639614   ║ \n",
      "  30 ║ 0.478297 │ -2.53037783068 ║ -5.29100513458 ║ 2.94e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.423074   ║ \n",
      "  31 ║ 0.478297 │ -2.53091641537 ║ -5.29268741608 ║ 5.60e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.509262   ║ \n",
      "  32 ║ 0.478297 │ -2.53138594858 ║ -5.29287290573 ║ 1.79e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.330391   ║ \n",
      "  33 ║ 0.478297 │ -2.53160232432 ║ -5.29328298569 ║ 1.59e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.296537   ║ \n",
      "  34 ║ 0.478297 │ -2.53175091377 ║ -5.29350566864 ║ 1.16e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.293898   ║ \n",
      "  35 ║ 0.478297 │ -2.53191857862 ║ -5.29381752014 ║ 9.79e-05 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.273829   ║ \n",
      "  36 ║ 0.478297 │ -2.53200210902 ║ -5.29413223267 ║ 1.65e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.375656   ║ \n",
      "  37 ║ 0.478297 │ -2.53222144606 ║ -5.29448413849 ║ 1.14e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.445341   ║ \n",
      "  38 ║ 0.478297 │ -2.53238578453 ║ -5.29486274719 ║ 1.31e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.385892   ║ \n",
      "  39 ║ 0.478297 │ -2.53239073039 ║ -5.29514980316 ║ 2.63e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.471347   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "     ║ <--- Penalty Function --> ║                ║ Total Violation ║ <--- Line Search ---> ║ <- Stationarity -> ║ \n",
      "Iter ║    Mu    │      Value     ║    Objective   ║   Ineq   │  Eq  ║ SD │ Evals │     t    ║ Grads │    Value   ║ \n",
      "═════╬═══════════════════════════╬════════════════╬═════════════════╬═══════════════════════╬════════════════════╣\n",
      "  40 ║ 0.478297 │ -2.53296333971 ║ -5.29616928101 ║ 1.78e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.313041   ║ \n",
      "  41 ║ 0.478297 │ -2.53312678353 ║ -5.29663991928 ║ 2.40e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.435326   ║ \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  42 ║ 0.430467 │ -2.28013898502 ║ -5.29768085480 ║ 3.39e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.397319   ║ \n",
      "  43 ║ 0.430467 │ -2.28024609279 ║ -5.29762601852 ║ 2.08e-04 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.323241   ║ \n",
      "  44 ║ 0.430467 │ -2.28044597618 ║ -5.29789733887 ║ 1.25e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.235920   ║ \n",
      "  45 ║ 0.430467 │ -2.28060165943 ║ -5.29813098907 ║ 7.00e-05 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.348329   ║ \n",
      "  46 ║ 0.430467 │ -2.28078929003 ║ -5.29859781265 ║ 8.33e-05 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.307751   ║ \n",
      "  47 ║ 0.430467 │ -2.28099150593 ║ -5.29904174805 ║ 7.22e-05 │   -  ║ S  │     2 │ 0.500000 ║     1 │ 0.280139   ║ \n",
      "  48 ║ 0.430467 │ -2.28100859374 ║ -5.29910373688 ║ 8.18e-05 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.304666   ║ \n",
      "  49 ║ 0.430467 │ -2.28118402230 ║ -5.29971647263 ║ 1.70e-04 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.280201   ║ \n",
      "  50 ║ 0.430467 │ -2.28143626977 ║ -5.30004692078 ║ 6.01e-05 │   -  ║ S  │     1 │ 1.000000 ║     1 │ 0.217794   ║ \n",
      "═════╩═══════════════════════════╩════════════════╩═════════════════╩═══════════════════════╩════════════════════╣\n",
      "Optimization results:                                                                                            ║ \n",
      "F = final iterate, B = Best (to tolerance), MF = Most Feasible                                                   ║ \n",
      "═════╦═══════════════════════════╦════════════════╦═════════════════╦═══════════════════════╦════════════════════╣\n",
      "   F ║          │                ║ -5.30004692078 ║ 6.01e-05 │   -  ║    │       │          ║       │            ║ \n",
      "   B ║          │                ║ -5.30004692078 ║ 6.01e-05 │   -  ║    │       │          ║       │            ║ \n",
      "  MF ║          │                ║ -4.98127365112 ║ 0.000000 │   -  ║    │       │          ║       │            ║ \n",
      "═════╩═══════════════════════════╩════════════════╩═════════════════╩═══════════════════════╩════════════════════╣\n",
      "Iterations:              50                                                                                      ║ \n",
      "Function evaluations:    68                                                                                      ║ \n",
      "PyGRANSO termination code: 4 --- max iterations reached.                                                         ║ \n",
      "═════════════════════════════════════════════════════════════════════════════════════════════════════════════════╝\n",
      "Total Wall Time: 7.217053413391113s\n"
     ]
    }
   ],
   "source": [
    "start = time.time()\n",
    "soln = pygranso(var_spec = var_in,combined_fn = comb_fn,user_opts = opts)\n",
    "end = time.time()\n",
    "print(\"Total Wall Time: {}s\".format(end - start))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9ba71567",
   "metadata": {},
   "source": [
    "### Results Visualization\n",
    "Visualize the original image and the perceptual attacked image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "4b85c0f4",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/buyun/anaconda3/envs/cuosqp_pygranso/lib/python3.9/site-packages/torch/nn/functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "def rescale_array(array):\n",
    "    ele_min, ele_max = np.amin(array), np.amax(array)\n",
    "    array = (array - ele_min) / (ele_max - ele_min)\n",
    "    return array\n",
    "\n",
    "def tensor2img(tensor):\n",
    "    tensor = torch.nn.functional.interpolate(\n",
    "        tensor,\n",
    "        scale_factor=3,\n",
    "        mode=\"bilinear\"\n",
    "    )\n",
    "    array = tensor.detach().cpu().numpy()[0, :, :, :]\n",
    "    array = np.transpose(array, [1, 2, 0])\n",
    "    return array\n",
    "\n",
    "final_adv_input = torch.reshape(soln.final.x,inputs.shape)\n",
    "\n",
    "ori_image = rescale_array(tensor2img(inputs))\n",
    "adv_image = rescale_array(tensor2img(final_adv_input))\n",
    "\n",
    "f = plt.figure()\n",
    "f.add_subplot(1,2,1)\n",
    "plt.imshow(ori_image)\n",
    "plt.title('Original Image')\n",
    "plt.axis('off')\n",
    "f.add_subplot(1,2,2)\n",
    "plt.imshow(adv_image)\n",
    "plt.title('Adversarial Attacked Image')\n",
    "plt.axis('off')\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}