Spaces:
Runtime error
Runtime error
santanupoddar
commited on
Commit
•
34841fa
1
Parent(s):
63208a3
new file ipynb
Browse files
Malware_Detection_with_Gradio-Final.ipynb
ADDED
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 4,
|
6 |
+
"id": "complete-wealth",
|
7 |
+
"metadata": {},
|
8 |
+
"outputs": [
|
9 |
+
{
|
10 |
+
"ename": "ContextualVersionConflict",
|
11 |
+
"evalue": "(anyio 2.2.0 (/opt/anaconda3/lib/python3.9/site-packages), Requirement.parse('anyio<4,>=3.0.0'), {'starlette'})",
|
12 |
+
"output_type": "error",
|
13 |
+
"traceback": [
|
14 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
15 |
+
"\u001b[0;31mContextualVersionConflict\u001b[0m Traceback (most recent call last)",
|
16 |
+
"\u001b[0;32m/var/folders/01/vtqqk20n4gq6wxn80d0ly7v80000gn/T/ipykernel_18714/2264163249.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mgradio\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mgr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpandas\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mmath\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msqrt\u001b[0m\u001b[0;34m;\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
17 |
+
"\u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/gradio/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mgradio\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstatic\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mButton\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mMarkdown\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m \u001b[0mcurrent_pkg_version\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpkg_resources\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequire\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"gradio\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mversion\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 16\u001b[0m \u001b[0m__version__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcurrent_pkg_version\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
18 |
+
"\u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pkg_resources/__init__.py\u001b[0m in \u001b[0;36mrequire\u001b[0;34m(self, *requirements)\u001b[0m\n\u001b[1;32m 884\u001b[0m \u001b[0mincluded\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0meven\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mthey\u001b[0m \u001b[0mwere\u001b[0m \u001b[0malready\u001b[0m \u001b[0mactivated\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mthis\u001b[0m \u001b[0mworking\u001b[0m \u001b[0mset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 885\u001b[0m \"\"\"\n\u001b[0;32m--> 886\u001b[0;31m \u001b[0mneeded\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresolve\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparse_requirements\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequirements\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 887\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 888\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mdist\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mneeded\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
19 |
+
"\u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pkg_resources/__init__.py\u001b[0m in \u001b[0;36mresolve\u001b[0;34m(self, requirements, env, installer, replace_conflicting, extras)\u001b[0m\n\u001b[1;32m 775\u001b[0m \u001b[0;31m# Oops, the \"best\" so far conflicts with a dependency\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 776\u001b[0m \u001b[0mdependent_req\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrequired_by\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mreq\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 777\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mVersionConflict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdist\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreq\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwith_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdependent_req\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 778\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 779\u001b[0m \u001b[0;31m# push the new requirements onto the stack\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
20 |
+
"\u001b[0;31mContextualVersionConflict\u001b[0m: (anyio 2.2.0 (/opt/anaconda3/lib/python3.9/site-packages), Requirement.parse('anyio<4,>=3.0.0'), {'starlette'})"
|
21 |
+
]
|
22 |
+
}
|
23 |
+
],
|
24 |
+
"source": [
|
25 |
+
"import gradio as gr\n",
|
26 |
+
"\n",
|
27 |
+
"\n",
|
28 |
+
"import pandas as pd\n",
|
29 |
+
"from math import sqrt;\n",
|
30 |
+
"from sklearn import preprocessing\n",
|
31 |
+
"from sklearn.ensemble import RandomForestClassifier\n",
|
32 |
+
"from sklearn.linear_model import LogisticRegression;\n",
|
33 |
+
"from sklearn.metrics import accuracy_score, r2_score, confusion_matrix, mean_absolute_error, mean_squared_error, f1_score, log_loss\n",
|
34 |
+
"from sklearn.model_selection import train_test_split\n",
|
35 |
+
"import numpy as np\n",
|
36 |
+
"import matplotlib.pyplot as plt\n",
|
37 |
+
"import seaborn as sns \n",
|
38 |
+
"import joblib\n",
|
39 |
+
" #load packages for ANN\n",
|
40 |
+
"import tensorflow as tf\n",
|
41 |
+
" \n",
|
42 |
+
"def malware_detection_DL (results, malicious_traffic, benign_traffic):\n",
|
43 |
+
" malicious_dataset = pd.read_csv(malicious_traffic) #Importing Datasets \n",
|
44 |
+
" benign_dataset = pd.read_csv(benign_traffic)\n",
|
45 |
+
" # Removing duplicated rows from benign_dataset (5380 rows removed)\n",
|
46 |
+
" benign_dataset = benign_dataset[benign_dataset.duplicated(keep=False) == False]\n",
|
47 |
+
" # Combining both datasets together\n",
|
48 |
+
" all_flows = pd.concat([malicious_dataset, benign_dataset])\n",
|
49 |
+
" # Reducing the size of the dataset to reduce the amount of time taken in training models\n",
|
50 |
+
" reduced_dataset = all_flows.sample(38000)\n",
|
51 |
+
" #dataset with columns with nan values dropped\n",
|
52 |
+
" df = reduced_dataset.drop(reduced_dataset.columns[np.isnan(reduced_dataset).any()], axis=1)\n",
|
53 |
+
" #### Isolating independent and dependent variables for training dataset\n",
|
54 |
+
" reduced_y = df['isMalware']\n",
|
55 |
+
" reduced_x = df.drop(['isMalware'], axis=1);\n",
|
56 |
+
" # Splitting datasets into training and test data\n",
|
57 |
+
" x_train, x_test, y_train, y_test = train_test_split(reduced_x, reduced_y, test_size=0.2, random_state=42)\n",
|
58 |
+
" \n",
|
59 |
+
" #scale data between 0 and 1\n",
|
60 |
+
" min_max_scaler = preprocessing.MinMaxScaler()\n",
|
61 |
+
" x_scale = min_max_scaler.fit_transform(reduced_x)\n",
|
62 |
+
" # Splitting datasets into training and test data\n",
|
63 |
+
" x_train, x_test, y_train, y_test = train_test_split(x_scale, reduced_y, test_size=0.2, random_state=42)\n",
|
64 |
+
" #type of layers in ann model is sequential, dense and uses relu activation \n",
|
65 |
+
" ann = tf.keras.models.Sequential()\n",
|
66 |
+
" model = tf.keras.Sequential([\n",
|
67 |
+
" tf.keras.layers.Dense(32, activation ='relu', input_shape=(373,)),\n",
|
68 |
+
" tf.keras.layers.Dense(32, activation = 'relu'),\n",
|
69 |
+
" tf.keras.layers.Dense(1, activation = 'sigmoid'),\n",
|
70 |
+
" ])\n",
|
71 |
+
" \n",
|
72 |
+
" \n",
|
73 |
+
" model.compile(optimizer ='adam', \n",
|
74 |
+
" loss = 'binary_crossentropy',\n",
|
75 |
+
" metrics = ['accuracy'])\n",
|
76 |
+
" #model.fit(x_train, y_train, batch_size=32, epochs = 150, validation_data=(x_test, y_test))\n",
|
77 |
+
" #does not output epochs and gives evalutaion of validation data and history of losses and accuracy\n",
|
78 |
+
" history = model.fit(x_train, y_train, batch_size=32, epochs = 150,verbose=0, validation_data=(x_test, y_test))\n",
|
79 |
+
" _, accuracy = model.evaluate(x_train, y_train)\n",
|
80 |
+
" #return history.history\n",
|
81 |
+
" if results==\"Accuracy\":\n",
|
82 |
+
" #summarize history for accuracy\n",
|
83 |
+
" plt.plot(history.history['accuracy'])\n",
|
84 |
+
" plt.plot(history.history['val_accuracy'])\n",
|
85 |
+
" plt.title('model accuracy')\n",
|
86 |
+
" plt.ylabel('accuracy')\n",
|
87 |
+
" plt.xlabel('epoch')\n",
|
88 |
+
" plt.legend(['train', 'test'], loc='upper left')\n",
|
89 |
+
" return plt.show()\n",
|
90 |
+
" else:\n",
|
91 |
+
" # summarize history for loss\n",
|
92 |
+
" plt.plot(history.history['loss'])\n",
|
93 |
+
" plt.plot(history.history['val_loss'])\n",
|
94 |
+
" plt.title('model loss')\n",
|
95 |
+
" plt.ylabel('loss')\n",
|
96 |
+
" plt.xlabel('epoch')\n",
|
97 |
+
" plt.legend(['train', 'test'], loc='upper left')\n",
|
98 |
+
" return plt.show()\n",
|
99 |
+
" \n",
|
100 |
+
" \n",
|
101 |
+
" \n",
|
102 |
+
"iface = gr.Interface(\n",
|
103 |
+
" malware_detection_DL, [gr.inputs.Dropdown([\"Accuracy\",\"Loss\"], label=\"Result Type\"),\n",
|
104 |
+
" gr.inputs.Dropdown([\"malicious_flows.csv\"], label = \"Malicious traffic in .csv\"), gr.inputs.Dropdown([\"sample_benign_flows.csv\"], label=\"Benign Traffic in .csv\")\n",
|
105 |
+
" ], \"plot\",\n",
|
106 |
+
" \n",
|
107 |
+
" \n",
|
108 |
+
")\n",
|
109 |
+
"\n",
|
110 |
+
"iface.launch()\n",
|
111 |
+
"\n"
|
112 |
+
]
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"cell_type": "code",
|
116 |
+
"execution_count": null,
|
117 |
+
"id": "curious-detector",
|
118 |
+
"metadata": {},
|
119 |
+
"outputs": [],
|
120 |
+
"source": []
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"cell_type": "code",
|
124 |
+
"execution_count": null,
|
125 |
+
"id": "2b934bff",
|
126 |
+
"metadata": {},
|
127 |
+
"outputs": [],
|
128 |
+
"source": []
|
129 |
+
}
|
130 |
+
],
|
131 |
+
"metadata": {
|
132 |
+
"kernelspec": {
|
133 |
+
"display_name": "Python 3 (ipykernel)",
|
134 |
+
"language": "python",
|
135 |
+
"name": "python3"
|
136 |
+
},
|
137 |
+
"language_info": {
|
138 |
+
"codemirror_mode": {
|
139 |
+
"name": "ipython",
|
140 |
+
"version": 3
|
141 |
+
},
|
142 |
+
"file_extension": ".py",
|
143 |
+
"mimetype": "text/x-python",
|
144 |
+
"name": "python",
|
145 |
+
"nbconvert_exporter": "python",
|
146 |
+
"pygments_lexer": "ipython3",
|
147 |
+
"version": "3.9.7"
|
148 |
+
}
|
149 |
+
},
|
150 |
+
"nbformat": 4,
|
151 |
+
"nbformat_minor": 5
|
152 |
+
}
|