-
Notifications
You must be signed in to change notification settings - Fork 2
/
training.html
862 lines (741 loc) · 41.9 KB
/
training.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1" />
<meta name="generator" content="pdoc 0.8.4" />
<title>training API documentation</title>
<meta name="description" content="" />
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/sanitize.min.css" integrity="sha256-PK9q560IAAa6WVRRh76LtCaI8pjTJ2z11v0miyNNjrs=" crossorigin>
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/typography.min.css" integrity="sha256-7l/o7C8jubJiy74VsKTidCy1yBkRtiUGbVkYBylBqUg=" crossorigin>
<link rel="stylesheet preload" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.18.1/styles/github.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-weight:bold;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em .5em;margin-bottom:1em}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.toc > ul > li{margin-top:.5em}}</style>
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.18.1/highlight.min.js" integrity="sha256-eOgo0OtLL4cdq7RdwRUiGKLX9XsIJ7nGhWEKbohmVAQ=" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => hljs.initHighlighting())</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>training</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">import numpy as np
import tensorflow as tf
from tensorflow.keras import layers, models, optimizers
from sklearn.metrics import confusion_matrix
from elasticsearch import Elasticsearch
import csv
def string_to_ascii(string):
"""
Function that converts the domain name to an integer array of ASCII values.
Args:
string: Contains the Domain Name entered by the user.
Returns:
A numpy array of ASCII values corresponding to the characters of the
Domain Name
"""
ascii_arr = np.zeros(len(string))
for i in range(len(string)):
ascii_arr[i] = ord(string[i])
return ascii_arr
def import_data(string_to_ascii, data_path, labels, header, lateral_skip,
no_of_entries, csv_txt):
"""
Function that imports data from both CSV files as well as TXT files.
Args:
string_to_ascii: Contains the string_to_ascii function.
data_path: Contains the path of the data to import.
labels: Contains the labels of the data that has to be imported.
header: Contains the number of lines to skip from the top.
lateral_skip: Contains the number of spaces to skip from the left.
no_of_entries: Contains the number of data entries that have to be
imported.
csv_txt: Contains whether the data to be imported is of a CSV file or a
TXT file.
Returns:
The data that has to be imported as well as the labels corresponding to
the data.
"""
if csv_txt == 0:
data = open(data_path, "r")
data = list(data.readlines())
else:
data = open(data_path, 'rt')
reader = csv.reader(data, delimiter=',', quoting=csv.QUOTE_NONE)
data = list(reader)
data = list(np.asarray(data[:no_of_entries + header])[:, 1])
ret_data = np.zeros((no_of_entries, 256))
for i in range(header, no_of_entries + header):
ret_data[i - header, 0: len(data[i].strip('\"'))] = \
string_to_ascii(data[i].strip('\"'))
labels = np.ones((no_of_entries, 1)) * labels
return ret_data, labels
def data_preprocessing(import_data, number_of_samples,
mal_data_address, benign_data_address):
"""
Function that returns the training dataset, the validation dataset as well
as the test dataset for model training and evaluation.
Args:
import_data: Contains the import_data function.
number_of_samples: Contains the number of data points that have to be
sampled for training.
mal_data_address: Contains the data path of malicious domains.
benign_data_address: Contains the data path of benign domains.
Returns:
The training dataset, the labels of the training dataset, the validation
dataset, the labels of the validation dataset, the test dataset as well
as the labels of the test dataset.
"""
ret_data_mal, labels_mal = \
import_data(string_to_ascii, mal_data_address, 1, 1, 0,
int(number_of_samples / 2), 0)
ret_data_nmal, labels_nmal = \
import_data(string_to_ascii, benign_data_address, 0, 1, 1,
int(number_of_samples / 2), 1)
train_split = int(number_of_samples / 2 * 0.8)
valid_split = int(number_of_samples / 2 * 0.9)
test_split = int(number_of_samples / 2)
train_set = np.append(ret_data_mal[0:train_split],
ret_data_nmal[0:train_split], axis=0)
train_set = np.reshape(train_set, (train_split * 2, 16, 16, 1))
np.random.seed(43)
np.random.shuffle(train_set)
labels_train_set = np.append(labels_mal[0:train_split],
labels_nmal[0:train_split], axis=0)
np.random.seed(43)
np.random.shuffle(labels_train_set)
valid_set = np.append(ret_data_mal[train_split:valid_split],
ret_data_nmal[train_split:valid_split], axis=0)
valid_set = np.reshape(valid_set, ((valid_split - train_split) * 2, 16, 16, 1))
np.random.seed(44)
np.random.shuffle(valid_set)
labels_valid_set = np.append(labels_mal[train_split:valid_split],
labels_nmal[train_split:valid_split], axis=0)
np.random.seed(44)
np.random.shuffle(labels_valid_set)
test_set = np.append(ret_data_mal[valid_split:test_split],
ret_data_nmal[valid_split:test_split], axis=0)
test_set = np.reshape(test_set, ((test_split - valid_split) * 2, 16, 16, 1))
np.random.seed(45)
np.random.shuffle(test_set)
labels_test_set = np.append(labels_mal[valid_split:test_split],
labels_nmal[valid_split:test_split], axis=0)
np.random.seed(45)
np.random.shuffle(labels_test_set)
print('Train Shape:', np.shape(train_set), np.shape(labels_train_set))
print('Validation Shape:', np.shape(valid_set), np.shape(labels_valid_set))
print('Test Shape:', np.shape(test_set), np.shape(labels_test_set))
return train_set, labels_train_set, valid_set, labels_valid_set, test_set, \
labels_test_set
def model_definition():
"""
Function that returns a Convolutional Neural Network that classifies whether
the domain name is malicious or benign.
Returns:
A Convolutional Neural Network that is a binary classifier that
classifies whether a domain name is malicious or benign.
"""
model = models.Sequential(name='DNS_Alert_Net')
model.add(layers.Conv2D(16, (2, 2), activation='relu',
input_shape=(16, 16, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(16, (2, 2), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(8, (2, 2), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(8, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
adam_ = tf.keras.optimizers.Adam(lr=0.001)
model.compile(loss='binary_crossentropy', optimizer=adam_,
metrics=['accuracy'])
return model
def training(es, model, model_name, epochs, batch_size, train_set,
labels_train_set, validation_set, labels_validation_set):
"""
Function that return the trained Convolutional Neural Network.
Args:
es: Contains the Elasticsearch object.
model: Contains the model as defined by the model_definition function.
model_name: Contains the model name.
epochs: Contains the number of epochs the model has to be trained for.
batch_size: Contains the batch size the model would use while training.
train_set: Contains the training dataset.
labels_train_set: Contains the labels for the training dataset.
validation_set: Contains the data for the validation dataset.
labels_validation_set: Contains the labels for the validation dataset.
Returns:
A trained binary classifier for identifying whether a domain is
malicious or benign.
"""
for i in range(epochs):
history = model.fit(train_set, labels_train_set, batch_size=batch_size,
epochs=1, validation_data=(validation_set,
labels_validation_set))
try:
body = es.get(index=es.get(index='model', id=1)['_source']['name'],
id=1)['_source']
body['training']['loss'].append(history.history['loss'][0] * 100)
body['training']['val_loss'].append(history.history['val_loss'][0] * 100)
body['training']['acc'].append(history.history['acc'][0] * 100)
body['training']['val_acc'].append(history.history['val_acc'][0] * 100)
body['training']['epochs'].append((i + 1))
update_body = {'doc':
{'training':
{'loss': (body['training']['loss']),
'val_loss': (body['training']['val_loss']),
'acc': (body['training']['acc']),
'val_acc': (body['training']['val_acc']),
'epochs': body['training']['epochs']
}
}
}
es.update(index=es.get(index='model', id=1)['_source']['name'],
id=1, body=update_body)
except:
print('Please check the Elasticsearch Server')
print('Training Completed')
return model
def model_evaluation_metrics(es, model, train_set, labels_train_set, valid_set,
labels_valid_set, test_set, labels_test_set):
"""
Function that updates the training accuracy graphs as well as loss graphs in
the Elasticsearch Database. The function also updates the confusion matrices
as well as the confusion metrics of the model, tested on the training,
validation as well as testing dataset, in the Elasticsearch Databse.
Args:
es: Contains the Elasticsearch object.
model: Contains the trained model.
train_set: Contains the training dataset.
labels_train_set: Contains the labels for the training dataset.
valid_set: Contains the data for the validation dataset.
labels_valid_set: Contains the labels for the validation dataset.
test_set: Contains the test dataset.
labels_test_set: Contains the labels for the test dataset.
Returns:
Not applicable.
"""
loss_train, acc_train = model.evaluate(train_set, labels_train_set)
loss_valid, acc_valid = model.evaluate(valid_set, labels_valid_set)
loss_test, acc_test = model.evaluate(test_set, labels_test_set)
y_pred = model.predict(train_set)
cf_matrix_train = confusion_matrix(labels_train_set, y_pred.round())
y_pred = model.predict(valid_set)
cf_matrix_valid = confusion_matrix(labels_valid_set, y_pred.round())
y_pred = model.predict(test_set)
cf_matrix_test = confusion_matrix(labels_test_set, y_pred.round())
acc_train = (cf_matrix_train[0, 0] + cf_matrix_train[1, 1]) / \
np.sum(cf_matrix_train)
pres_train = (cf_matrix_train[1, 1]) / (cf_matrix_train[1, 1] +
cf_matrix_train[0, 1])
rec_train = (cf_matrix_train[1, 1]) / (cf_matrix_train[1, 1] +
cf_matrix_train[1, 0])
f1_train = 2 * rec_train * pres_train / (rec_train + pres_train)
acc_valid = (cf_matrix_valid[0, 0] + cf_matrix_valid[1, 1]) / \
np.sum(cf_matrix_valid)
pres_valid = (cf_matrix_valid[1, 1]) / (cf_matrix_valid[1, 1] +
cf_matrix_valid[0, 1])
rec_valid = (cf_matrix_valid[1, 1]) / (cf_matrix_valid[1, 1] +
cf_matrix_valid[1, 0])
f1_valid = 2 * rec_valid * pres_valid / (rec_valid + pres_valid)
acc_test = (cf_matrix_test[0, 0] + cf_matrix_test[1, 1]) / \
np.sum(cf_matrix_test)
pres_test = (cf_matrix_test[1, 1]) / (cf_matrix_test[1, 1] +
cf_matrix_test[0, 1])
rec_test = (cf_matrix_test[1, 1]) / (cf_matrix_test[1, 1] +
cf_matrix_test[1, 0])
f1_test = 2 * rec_test * pres_test / (rec_test + pres_test)
update_body = {'doc':
{'metrics':
{'loss_train': loss_train, 'acc_train': acc_train,
'loss_valid': loss_valid, 'acc_valid': acc_valid,
'loss_test': loss_test, 'acc_test': acc_test,
'cf_matrix_train': cf_matrix_train, 'cf_matrix_valid': cf_matrix_valid,
'cf_matrix_test': cf_matrix_test,
'pres_train': pres_train, 'rec_train': rec_train, 'f1_train': f1_train,
'pres_valid': pres_valid, 'rec_valid': rec_valid, 'f1_valid': f1_valid,
'pres_test': pres_test, 'rec_test': rec_test, 'f1_test': f1_test
}
}
}
try:
es.update(index=es.get(index='model', id=1)['_source']['name'], id=1,
body=update_body)
except:
print('Please check the Elasticsearch Server')
if __name__ == '__main__':
es = Elasticsearch()
mal_data_path = '../data/malicious_domains.txt'
benign_data_path = '../data/benign_domains.csv'
train_set, labels_train_set, valid_set, labels_valid_set, test_set, \
labels_test_set = data_preprocessing(import_data, 1000,
mal_data_path, benign_data_path)
while True:
training_ = es.get(index='model', id=1)['_source']['training']
if training_:
body = {'training': {'loss': [], 'val_loss': [], 'acc': [],
'val_acc': [], 'epochs': []},
'metrics': {'loss_train': 0, 'acc_train': 0, 'loss_valid': 0,
'acc_valid': 0, 'loss_test': 0, 'acc_test': 0,
'cf_matrix_train': 0, 'cf_matrix_valid': 0, 'cf_matrix_test': 0,
'pres_train': 0, 'rec_train': 0, 'f1_train': 0,
'pres_valid': 0, 'rec_valid': 0, 'f1_valid': 0,
'pres_test': 0, 'rec_test': 0, 'f1_test': 0}}
es.index(index=es.get(index='model', id=1)['_source']['name'], id=1, body=body)
model = model_definition()
trained_model = training(es, model, es.get(index='model', id=1)['_source']['name'],
es.get(index='model', id=1)['_source']['epochs'],
es.get(index='model', id=1)['_source']['batch'],
train_set, labels_train_set, valid_set, labels_valid_set)
model_evaluation_metrics(es, trained_model, train_set, labels_train_set,
valid_set, labels_valid_set, test_set, labels_test_set)
name = es.get(index='model', id=1)['_source']['name']
model.save('../saved_models/' + name + '.hdf5')
update_body = {'doc': {'completed': 1, 'training': 0}}
es.update(index='model', id=1, body=update_body)</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-functions">Functions</h2>
<dl>
<dt id="training.data_preprocessing"><code class="name flex">
<span>def <span class="ident">data_preprocessing</span></span>(<span>import_data, number_of_samples, mal_data_address, benign_data_address)</span>
</code></dt>
<dd>
<div class="desc"><p>Function that returns the training dataset, the validation dataset as well
as the test dataset for model training and evaluation.</p>
<h2 id="args">Args</h2>
<dl>
<dt><strong><code>import_data</code></strong></dt>
<dd>Contains the import_data function.</dd>
<dt><strong><code>number_of_samples</code></strong></dt>
<dd>Contains the number of data points that have to be
sampled for training.</dd>
<dt><strong><code>mal_data_address</code></strong></dt>
<dd>Contains the data path of malicious domains.</dd>
<dt><strong><code>benign_data_address</code></strong></dt>
<dd>Contains the data path of benign domains.</dd>
</dl>
<h2 id="returns">Returns</h2>
<p>The training dataset, the labels of the training dataset, the validation
dataset, the labels of the validation dataset, the test dataset as well
as the labels of the test dataset.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def data_preprocessing(import_data, number_of_samples,
mal_data_address, benign_data_address):
"""
Function that returns the training dataset, the validation dataset as well
as the test dataset for model training and evaluation.
Args:
import_data: Contains the import_data function.
number_of_samples: Contains the number of data points that have to be
sampled for training.
mal_data_address: Contains the data path of malicious domains.
benign_data_address: Contains the data path of benign domains.
Returns:
The training dataset, the labels of the training dataset, the validation
dataset, the labels of the validation dataset, the test dataset as well
as the labels of the test dataset.
"""
ret_data_mal, labels_mal = \
import_data(string_to_ascii, mal_data_address, 1, 1, 0,
int(number_of_samples / 2), 0)
ret_data_nmal, labels_nmal = \
import_data(string_to_ascii, benign_data_address, 0, 1, 1,
int(number_of_samples / 2), 1)
train_split = int(number_of_samples / 2 * 0.8)
valid_split = int(number_of_samples / 2 * 0.9)
test_split = int(number_of_samples / 2)
train_set = np.append(ret_data_mal[0:train_split],
ret_data_nmal[0:train_split], axis=0)
train_set = np.reshape(train_set, (train_split * 2, 16, 16, 1))
np.random.seed(43)
np.random.shuffle(train_set)
labels_train_set = np.append(labels_mal[0:train_split],
labels_nmal[0:train_split], axis=0)
np.random.seed(43)
np.random.shuffle(labels_train_set)
valid_set = np.append(ret_data_mal[train_split:valid_split],
ret_data_nmal[train_split:valid_split], axis=0)
valid_set = np.reshape(valid_set, ((valid_split - train_split) * 2, 16, 16, 1))
np.random.seed(44)
np.random.shuffle(valid_set)
labels_valid_set = np.append(labels_mal[train_split:valid_split],
labels_nmal[train_split:valid_split], axis=0)
np.random.seed(44)
np.random.shuffle(labels_valid_set)
test_set = np.append(ret_data_mal[valid_split:test_split],
ret_data_nmal[valid_split:test_split], axis=0)
test_set = np.reshape(test_set, ((test_split - valid_split) * 2, 16, 16, 1))
np.random.seed(45)
np.random.shuffle(test_set)
labels_test_set = np.append(labels_mal[valid_split:test_split],
labels_nmal[valid_split:test_split], axis=0)
np.random.seed(45)
np.random.shuffle(labels_test_set)
print('Train Shape:', np.shape(train_set), np.shape(labels_train_set))
print('Validation Shape:', np.shape(valid_set), np.shape(labels_valid_set))
print('Test Shape:', np.shape(test_set), np.shape(labels_test_set))
return train_set, labels_train_set, valid_set, labels_valid_set, test_set, \
labels_test_set</code></pre>
</details>
</dd>
<dt id="training.import_data"><code class="name flex">
<span>def <span class="ident">import_data</span></span>(<span>string_to_ascii, data_path, labels, header, lateral_skip, no_of_entries, csv_txt)</span>
</code></dt>
<dd>
<div class="desc"><p>Function that imports data from both CSV files as well as TXT files.</p>
<h2 id="args">Args</h2>
<dl>
<dt><strong><code>string_to_ascii</code></strong></dt>
<dd>Contains the string_to_ascii function.</dd>
<dt><strong><code>data_path</code></strong></dt>
<dd>Contains the path of the data to import.</dd>
<dt><strong><code>labels</code></strong></dt>
<dd>Contains the labels of the data that has to be imported.</dd>
<dt><strong><code>header</code></strong></dt>
<dd>Contains the number of lines to skip from the top.</dd>
<dt><strong><code>lateral_skip</code></strong></dt>
<dd>Contains the number of spaces to skip from the left.</dd>
<dt><strong><code>no_of_entries</code></strong></dt>
<dd>Contains the number of data entries that have to be
imported.</dd>
<dt><strong><code>csv_txt</code></strong></dt>
<dd>Contains whether the data to be imported is of a CSV file or a
TXT file.</dd>
</dl>
<h2 id="returns">Returns</h2>
<p>The data that has to be imported as well as the labels corresponding to
the data.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def import_data(string_to_ascii, data_path, labels, header, lateral_skip,
no_of_entries, csv_txt):
"""
Function that imports data from both CSV files as well as TXT files.
Args:
string_to_ascii: Contains the string_to_ascii function.
data_path: Contains the path of the data to import.
labels: Contains the labels of the data that has to be imported.
header: Contains the number of lines to skip from the top.
lateral_skip: Contains the number of spaces to skip from the left.
no_of_entries: Contains the number of data entries that have to be
imported.
csv_txt: Contains whether the data to be imported is of a CSV file or a
TXT file.
Returns:
The data that has to be imported as well as the labels corresponding to
the data.
"""
if csv_txt == 0:
data = open(data_path, "r")
data = list(data.readlines())
else:
data = open(data_path, 'rt')
reader = csv.reader(data, delimiter=',', quoting=csv.QUOTE_NONE)
data = list(reader)
data = list(np.asarray(data[:no_of_entries + header])[:, 1])
ret_data = np.zeros((no_of_entries, 256))
for i in range(header, no_of_entries + header):
ret_data[i - header, 0: len(data[i].strip('\"'))] = \
string_to_ascii(data[i].strip('\"'))
labels = np.ones((no_of_entries, 1)) * labels
return ret_data, labels</code></pre>
</details>
</dd>
<dt id="training.model_definition"><code class="name flex">
<span>def <span class="ident">model_definition</span></span>(<span>)</span>
</code></dt>
<dd>
<div class="desc"><p>Function that returns a Convolutional Neural Network that classifies whether
the domain name is malicious or benign.</p>
<h2 id="returns">Returns</h2>
<p>A Convolutional Neural Network that is a binary classifier that
classifies whether a domain name is malicious or benign.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def model_definition():
"""
Function that returns a Convolutional Neural Network that classifies whether
the domain name is malicious or benign.
Returns:
A Convolutional Neural Network that is a binary classifier that
classifies whether a domain name is malicious or benign.
"""
model = models.Sequential(name='DNS_Alert_Net')
model.add(layers.Conv2D(16, (2, 2), activation='relu',
input_shape=(16, 16, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(16, (2, 2), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(8, (2, 2), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(8, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
adam_ = tf.keras.optimizers.Adam(lr=0.001)
model.compile(loss='binary_crossentropy', optimizer=adam_,
metrics=['accuracy'])
return model</code></pre>
</details>
</dd>
<dt id="training.model_evaluation_metrics"><code class="name flex">
<span>def <span class="ident">model_evaluation_metrics</span></span>(<span>es, model, train_set, labels_train_set, valid_set, labels_valid_set, test_set, labels_test_set)</span>
</code></dt>
<dd>
<div class="desc"><p>Function that updates the training accuracy graphs as well as loss graphs in
the Elasticsearch Database. The function also updates the confusion matrices
as well as the confusion metrics of the model, tested on the training,
validation as well as testing dataset, in the Elasticsearch Databse.</p>
<h2 id="args">Args</h2>
<dl>
<dt><strong><code>es</code></strong></dt>
<dd>Contains the Elasticsearch object.</dd>
<dt><strong><code>model</code></strong></dt>
<dd>Contains the trained model.</dd>
<dt><strong><code>train_set</code></strong></dt>
<dd>Contains the training dataset.</dd>
<dt><strong><code>labels_train_set</code></strong></dt>
<dd>Contains the labels for the training dataset.</dd>
<dt><strong><code>valid_set</code></strong></dt>
<dd>Contains the data for the validation dataset.</dd>
<dt><strong><code>labels_valid_set</code></strong></dt>
<dd>Contains the labels for the validation dataset.</dd>
<dt><strong><code>test_set</code></strong></dt>
<dd>Contains the test dataset.</dd>
<dt><strong><code>labels_test_set</code></strong></dt>
<dd>Contains the labels for the test dataset.</dd>
</dl>
<h2 id="returns">Returns</h2>
<p>Not applicable.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def model_evaluation_metrics(es, model, train_set, labels_train_set, valid_set,
labels_valid_set, test_set, labels_test_set):
"""
Function that updates the training accuracy graphs as well as loss graphs in
the Elasticsearch Database. The function also updates the confusion matrices
as well as the confusion metrics of the model, tested on the training,
validation as well as testing dataset, in the Elasticsearch Databse.
Args:
es: Contains the Elasticsearch object.
model: Contains the trained model.
train_set: Contains the training dataset.
labels_train_set: Contains the labels for the training dataset.
valid_set: Contains the data for the validation dataset.
labels_valid_set: Contains the labels for the validation dataset.
test_set: Contains the test dataset.
labels_test_set: Contains the labels for the test dataset.
Returns:
Not applicable.
"""
loss_train, acc_train = model.evaluate(train_set, labels_train_set)
loss_valid, acc_valid = model.evaluate(valid_set, labels_valid_set)
loss_test, acc_test = model.evaluate(test_set, labels_test_set)
y_pred = model.predict(train_set)
cf_matrix_train = confusion_matrix(labels_train_set, y_pred.round())
y_pred = model.predict(valid_set)
cf_matrix_valid = confusion_matrix(labels_valid_set, y_pred.round())
y_pred = model.predict(test_set)
cf_matrix_test = confusion_matrix(labels_test_set, y_pred.round())
acc_train = (cf_matrix_train[0, 0] + cf_matrix_train[1, 1]) / \
np.sum(cf_matrix_train)
pres_train = (cf_matrix_train[1, 1]) / (cf_matrix_train[1, 1] +
cf_matrix_train[0, 1])
rec_train = (cf_matrix_train[1, 1]) / (cf_matrix_train[1, 1] +
cf_matrix_train[1, 0])
f1_train = 2 * rec_train * pres_train / (rec_train + pres_train)
acc_valid = (cf_matrix_valid[0, 0] + cf_matrix_valid[1, 1]) / \
np.sum(cf_matrix_valid)
pres_valid = (cf_matrix_valid[1, 1]) / (cf_matrix_valid[1, 1] +
cf_matrix_valid[0, 1])
rec_valid = (cf_matrix_valid[1, 1]) / (cf_matrix_valid[1, 1] +
cf_matrix_valid[1, 0])
f1_valid = 2 * rec_valid * pres_valid / (rec_valid + pres_valid)
acc_test = (cf_matrix_test[0, 0] + cf_matrix_test[1, 1]) / \
np.sum(cf_matrix_test)
pres_test = (cf_matrix_test[1, 1]) / (cf_matrix_test[1, 1] +
cf_matrix_test[0, 1])
rec_test = (cf_matrix_test[1, 1]) / (cf_matrix_test[1, 1] +
cf_matrix_test[1, 0])
f1_test = 2 * rec_test * pres_test / (rec_test + pres_test)
update_body = {'doc':
{'metrics':
{'loss_train': loss_train, 'acc_train': acc_train,
'loss_valid': loss_valid, 'acc_valid': acc_valid,
'loss_test': loss_test, 'acc_test': acc_test,
'cf_matrix_train': cf_matrix_train, 'cf_matrix_valid': cf_matrix_valid,
'cf_matrix_test': cf_matrix_test,
'pres_train': pres_train, 'rec_train': rec_train, 'f1_train': f1_train,
'pres_valid': pres_valid, 'rec_valid': rec_valid, 'f1_valid': f1_valid,
'pres_test': pres_test, 'rec_test': rec_test, 'f1_test': f1_test
}
}
}
try:
es.update(index=es.get(index='model', id=1)['_source']['name'], id=1,
body=update_body)
except:
print('Please check the Elasticsearch Server')</code></pre>
</details>
</dd>
<dt id="training.string_to_ascii"><code class="name flex">
<span>def <span class="ident">string_to_ascii</span></span>(<span>string)</span>
</code></dt>
<dd>
<div class="desc"><p>Function that converts the domain name to an integer array of ASCII values.</p>
<h2 id="args">Args</h2>
<dl>
<dt><strong><code>string</code></strong></dt>
<dd>Contains the Domain Name entered by the user.</dd>
</dl>
<h2 id="returns">Returns</h2>
<p>A numpy array of ASCII values corresponding to the characters of the
Domain Name</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def string_to_ascii(string):
"""
Function that converts the domain name to an integer array of ASCII values.
Args:
string: Contains the Domain Name entered by the user.
Returns:
A numpy array of ASCII values corresponding to the characters of the
Domain Name
"""
ascii_arr = np.zeros(len(string))
for i in range(len(string)):
ascii_arr[i] = ord(string[i])
return ascii_arr</code></pre>
</details>
</dd>
<dt id="training.training"><code class="name flex">
<span>def <span class="ident">training</span></span>(<span>es, model, model_name, epochs, batch_size, train_set, labels_train_set, validation_set, labels_validation_set)</span>
</code></dt>
<dd>
<div class="desc"><p>Function that return the trained Convolutional Neural Network.</p>
<h2 id="args">Args</h2>
<dl>
<dt><strong><code>es</code></strong></dt>
<dd>Contains the Elasticsearch object.</dd>
<dt><strong><code>model</code></strong></dt>
<dd>Contains the model as defined by the model_definition function.</dd>
<dt><strong><code>model_name</code></strong></dt>
<dd>Contains the model name.</dd>
<dt><strong><code>epochs</code></strong></dt>
<dd>Contains the number of epochs the model has to be trained for.</dd>
<dt><strong><code>batch_size</code></strong></dt>
<dd>Contains the batch size the model would use while training.</dd>
<dt><strong><code>train_set</code></strong></dt>
<dd>Contains the training dataset.</dd>
<dt><strong><code>labels_train_set</code></strong></dt>
<dd>Contains the labels for the training dataset.</dd>
<dt><strong><code>validation_set</code></strong></dt>
<dd>Contains the data for the validation dataset.</dd>
<dt><strong><code>labels_validation_set</code></strong></dt>
<dd>Contains the labels for the validation dataset.</dd>
</dl>
<h2 id="returns">Returns</h2>
<p>A trained binary classifier for identifying whether a domain is
malicious or benign.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def training(es, model, model_name, epochs, batch_size, train_set,
labels_train_set, validation_set, labels_validation_set):
"""
Function that return the trained Convolutional Neural Network.
Args:
es: Contains the Elasticsearch object.
model: Contains the model as defined by the model_definition function.
model_name: Contains the model name.
epochs: Contains the number of epochs the model has to be trained for.
batch_size: Contains the batch size the model would use while training.
train_set: Contains the training dataset.
labels_train_set: Contains the labels for the training dataset.
validation_set: Contains the data for the validation dataset.
labels_validation_set: Contains the labels for the validation dataset.
Returns:
A trained binary classifier for identifying whether a domain is
malicious or benign.
"""
for i in range(epochs):
history = model.fit(train_set, labels_train_set, batch_size=batch_size,
epochs=1, validation_data=(validation_set,
labels_validation_set))
try:
body = es.get(index=es.get(index='model', id=1)['_source']['name'],
id=1)['_source']
body['training']['loss'].append(history.history['loss'][0] * 100)
body['training']['val_loss'].append(history.history['val_loss'][0] * 100)
body['training']['acc'].append(history.history['acc'][0] * 100)
body['training']['val_acc'].append(history.history['val_acc'][0] * 100)
body['training']['epochs'].append((i + 1))
update_body = {'doc':
{'training':
{'loss': (body['training']['loss']),
'val_loss': (body['training']['val_loss']),
'acc': (body['training']['acc']),
'val_acc': (body['training']['val_acc']),
'epochs': body['training']['epochs']
}
}
}
es.update(index=es.get(index='model', id=1)['_source']['name'],
id=1, body=update_body)
except:
print('Please check the Elasticsearch Server')
print('Training Completed')
return model</code></pre>
</details>
</dd>
</dl>
</section>
<section>
</section>
</article>
<nav id="sidebar">
<h1>Index</h1>
<div class="toc">
<ul></ul>
</div>
<ul id="index">
<li><h3><a href="#header-functions">Functions</a></h3>
<ul class="">
<li><code><a title="training.data_preprocessing" href="#training.data_preprocessing">data_preprocessing</a></code></li>
<li><code><a title="training.import_data" href="#training.import_data">import_data</a></code></li>
<li><code><a title="training.model_definition" href="#training.model_definition">model_definition</a></code></li>
<li><code><a title="training.model_evaluation_metrics" href="#training.model_evaluation_metrics">model_evaluation_metrics</a></code></li>
<li><code><a title="training.string_to_ascii" href="#training.string_to_ascii">string_to_ascii</a></code></li>
<li><code><a title="training.training" href="#training.training">training</a></code></li>
</ul>
</li>
</ul>
</nav>
</main>
<footer id="footer">
<p>Generated by <a href="https://pdoc3.github.io/pdoc"><cite>pdoc</cite> 0.8.4</a>.</p>
</footer>
</body>
</html>