AmirlyPhd/final_V2-bert-after-adding-new-words-text-classification-model
Browse files- README.md +92 -0
- added_tokens.json +121 -0
- config.json +45 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1121 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
- f1
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
model-index:
|
10 |
+
- name: final_V2-bert-after-adding-new-words-text-classification-model
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# final_V2-bert-after-adding-new-words-text-classification-model
|
18 |
+
|
19 |
+
This model was trained from scratch on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1494
|
22 |
+
- Accuracy: 0.9716
|
23 |
+
- F1: 0.8348
|
24 |
+
- Precision: 0.8317
|
25 |
+
- Recall: 0.8385
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 5e-05
|
45 |
+
- train_batch_size: 16
|
46 |
+
- eval_batch_size: 32
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- lr_scheduler_warmup_steps: 100
|
51 |
+
- num_epochs: 3
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| 1.8136 | 0.11 | 50 | 1.7501 | 0.3470 | 0.1733 | 0.3034 | 0.1944 |
|
59 |
+
| 0.9023 | 0.22 | 100 | 1.2121 | 0.5723 | 0.3083 | 0.3496 | 0.3189 |
|
60 |
+
| 0.5924 | 0.33 | 150 | 0.9662 | 0.6667 | 0.3919 | 0.4265 | 0.4037 |
|
61 |
+
| 0.4218 | 0.44 | 200 | 0.4848 | 0.8813 | 0.6427 | 0.6492 | 0.6413 |
|
62 |
+
| 0.2025 | 0.55 | 250 | 0.3807 | 0.9021 | 0.6677 | 0.6538 | 0.6829 |
|
63 |
+
| 0.1609 | 0.66 | 300 | 0.3360 | 0.9147 | 0.6763 | 0.6727 | 0.6822 |
|
64 |
+
| 0.2035 | 0.76 | 350 | 0.3705 | 0.8991 | 0.6711 | 0.6589 | 0.6838 |
|
65 |
+
| 0.1208 | 0.87 | 400 | 0.2140 | 0.9565 | 0.8218 | 0.8137 | 0.8323 |
|
66 |
+
| 0.1313 | 0.98 | 450 | 0.6818 | 0.8704 | 0.6779 | 0.7179 | 0.6859 |
|
67 |
+
| 0.1576 | 1.09 | 500 | 0.2508 | 0.9212 | 0.7443 | 0.7888 | 0.7311 |
|
68 |
+
| 0.0593 | 1.2 | 550 | 0.2091 | 0.9552 | 0.8193 | 0.8179 | 0.8227 |
|
69 |
+
| 0.0705 | 1.31 | 600 | 0.2010 | 0.9552 | 0.8154 | 0.8091 | 0.8225 |
|
70 |
+
| 0.0637 | 1.42 | 650 | 0.1985 | 0.9573 | 0.8187 | 0.8115 | 0.8275 |
|
71 |
+
| 0.0619 | 1.53 | 700 | 0.2306 | 0.9541 | 0.8241 | 0.8194 | 0.8301 |
|
72 |
+
| 0.0582 | 1.64 | 750 | 0.2001 | 0.9609 | 0.8280 | 0.8250 | 0.8320 |
|
73 |
+
| 0.1132 | 1.75 | 800 | 0.1439 | 0.9680 | 0.8324 | 0.8284 | 0.8367 |
|
74 |
+
| 0.0416 | 1.86 | 850 | 0.1558 | 0.9680 | 0.8333 | 0.8301 | 0.8369 |
|
75 |
+
| 0.0371 | 1.97 | 900 | 0.2242 | 0.9595 | 0.8280 | 0.8235 | 0.8345 |
|
76 |
+
| 0.0428 | 2.07 | 950 | 0.1907 | 0.9617 | 0.8303 | 0.8262 | 0.8356 |
|
77 |
+
| 0.0388 | 2.18 | 1000 | 0.1784 | 0.9658 | 0.8319 | 0.8266 | 0.8383 |
|
78 |
+
| 0.0335 | 2.29 | 1050 | 0.1735 | 0.9675 | 0.8323 | 0.8266 | 0.8390 |
|
79 |
+
| 0.0361 | 2.4 | 1100 | 0.1921 | 0.9636 | 0.8283 | 0.8219 | 0.8360 |
|
80 |
+
| 0.0126 | 2.51 | 1150 | 0.2200 | 0.9614 | 0.8294 | 0.8274 | 0.8327 |
|
81 |
+
| 0.003 | 2.62 | 1200 | 0.2251 | 0.9614 | 0.8296 | 0.8262 | 0.8346 |
|
82 |
+
| 0.0029 | 2.73 | 1250 | 0.1750 | 0.9694 | 0.8348 | 0.8314 | 0.8388 |
|
83 |
+
| 0.0137 | 2.84 | 1300 | 0.1775 | 0.9686 | 0.8345 | 0.8300 | 0.8397 |
|
84 |
+
| 0.0184 | 2.95 | 1350 | 0.1860 | 0.9675 | 0.8337 | 0.8293 | 0.8391 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.39.3
|
90 |
+
- Pytorch 2.1.2
|
91 |
+
- Datasets 2.18.0
|
92 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"2fa": 30635,
|
3 |
+
"ad fraud": 30565,
|
4 |
+
"advanced persistent threat": 30571,
|
5 |
+
"advanced threat protection": 30572,
|
6 |
+
"adware": 30573,
|
7 |
+
"anti-botnet": 30574,
|
8 |
+
"anti-malware": 30575,
|
9 |
+
"anti-phishing": 30576,
|
10 |
+
"anti-virus": 30577,
|
11 |
+
"attack vector": 30578,
|
12 |
+
"backdoor": 30536,
|
13 |
+
"banker trojan": 30579,
|
14 |
+
"black hat": 30639,
|
15 |
+
"blacklist": 30580,
|
16 |
+
"botnet": 30527,
|
17 |
+
"browser hijacking": 30560,
|
18 |
+
"brute force attack": 30538,
|
19 |
+
"buffer overflow": 30543,
|
20 |
+
"business continuity plan": 30581,
|
21 |
+
"business disruption": 30582,
|
22 |
+
"byoc": 30583,
|
23 |
+
"byod": 30584,
|
24 |
+
"byol": 30585,
|
25 |
+
"captcha": 30586,
|
26 |
+
"click fraud": 30564,
|
27 |
+
"click jacking": 30544,
|
28 |
+
"clickjacking": 30587,
|
29 |
+
"clientless": 30588,
|
30 |
+
"code injection": 30589,
|
31 |
+
"cots": 30590,
|
32 |
+
"credential harvesting": 30561,
|
33 |
+
"credential stuffing": 30537,
|
34 |
+
"critical infrastructure": 30591,
|
35 |
+
"cross-site scripting": 30530,
|
36 |
+
"cryptojacking": 30539,
|
37 |
+
"cyber espionage": 30546,
|
38 |
+
"cyber extortion": 30554,
|
39 |
+
"cyber stalking": 30552,
|
40 |
+
"cyberbullying": 30592,
|
41 |
+
"cybercrime": 30640,
|
42 |
+
"cybersecurity": 30593,
|
43 |
+
"dark web": 30594,
|
44 |
+
"data breach": 30540,
|
45 |
+
"data integrity": 30595,
|
46 |
+
"data theft": 30597,
|
47 |
+
"ddos": 30528,
|
48 |
+
"decryption": 30598,
|
49 |
+
"detection and response": 30599,
|
50 |
+
"digital forensics": 30600,
|
51 |
+
"digital transformation": 30601,
|
52 |
+
"dlp": 30596,
|
53 |
+
"dns": 30602,
|
54 |
+
"dns hijacking": 30567,
|
55 |
+
"dns spoofing": 30550,
|
56 |
+
"drive-by download": 30556,
|
57 |
+
"drive-by download attack": 30603,
|
58 |
+
"eavesdropping": 30553,
|
59 |
+
"endpoint protection": 30604,
|
60 |
+
"fido": 30605,
|
61 |
+
"file injection": 30562,
|
62 |
+
"fileless malware": 30557,
|
63 |
+
"firewall": 30606,
|
64 |
+
"formgrabbing": 30566,
|
65 |
+
"formjacking": 30545,
|
66 |
+
"greylist": 30607,
|
67 |
+
"honeypot": 30608,
|
68 |
+
"iam": 30609,
|
69 |
+
"identity theft": 30541,
|
70 |
+
"in-line network device": 30610,
|
71 |
+
"insider threat": 30611,
|
72 |
+
"iot": 30613,
|
73 |
+
"ips": 30612,
|
74 |
+
"keylogger": 30534,
|
75 |
+
"logic bomb": 30558,
|
76 |
+
"macroviruses": 30568,
|
77 |
+
"malvertising": 30563,
|
78 |
+
"malware": 30525,
|
79 |
+
"man-in-the-middle": 30614,
|
80 |
+
"man-in-the-middle attack": 30531,
|
81 |
+
"packet sniffing": 30569,
|
82 |
+
"parental controls": 30615,
|
83 |
+
"pen testing": 30616,
|
84 |
+
"pharming": 30559,
|
85 |
+
"phishing": 30524,
|
86 |
+
"pii": 30617,
|
87 |
+
"process hollowing": 30618,
|
88 |
+
"ram scraping": 30570,
|
89 |
+
"ransomware": 30522,
|
90 |
+
"rdp": 30619,
|
91 |
+
"risktool": 30620,
|
92 |
+
"rootkit": 30535,
|
93 |
+
"sandbox": 30621,
|
94 |
+
"scareware": 30622,
|
95 |
+
"secaas": 30623,
|
96 |
+
"security incident response": 30625,
|
97 |
+
"security perimeter": 30626,
|
98 |
+
"session hijacking": 30551,
|
99 |
+
"siem": 30627,
|
100 |
+
"sim swapping": 30628,
|
101 |
+
"smishing": 30548,
|
102 |
+
"soar": 30629,
|
103 |
+
"social engineering": 30532,
|
104 |
+
"spam": 30630,
|
105 |
+
"spear phishing": 30631,
|
106 |
+
"spoofing": 30542,
|
107 |
+
"spyware": 30526,
|
108 |
+
"sql injection": 30529,
|
109 |
+
"ssl": 30624,
|
110 |
+
"threat assessment": 30632,
|
111 |
+
"threat hunting": 30633,
|
112 |
+
"threat intelligence": 30634,
|
113 |
+
"typosquatting": 30555,
|
114 |
+
"url": 30523,
|
115 |
+
"vishing": 30547,
|
116 |
+
"vpn": 30636,
|
117 |
+
"waf": 30637,
|
118 |
+
"watering hole attack": 30549,
|
119 |
+
"white hat": 30638,
|
120 |
+
"zero-day exploit": 30533
|
121 |
+
}
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/kaggle/working/bert_model_after_adding_new_words",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5,
|
30 |
+
"LABEL_6": 6
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"model_type": "bert",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 0,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"problem_type": "single_label_classification",
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.39.3",
|
42 |
+
"type_vocab_size": 2,
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 30641
|
45 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81eab6535eae8f4d3cd05f897a1aa9cdfeac2164a2020e5baade62e39fb0c57c
|
3 |
+
size 438339596
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,1121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"7865": {
|
44 |
+
"content": "virus",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"8983": {
|
52 |
+
"content": "patch",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"15485": {
|
60 |
+
"content": "worm",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"18077": {
|
68 |
+
"content": "exploit",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"18130": {
|
76 |
+
"content": "vulnerability",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"21999": {
|
84 |
+
"content": "encryption",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"23307": {
|
92 |
+
"content": "hacker",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"23445": {
|
100 |
+
"content": "trojan",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"23687": {
|
108 |
+
"content": "whaling",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"25941": {
|
116 |
+
"content": "ioc",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"27084": {
|
124 |
+
"content": "soc",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"27280": {
|
132 |
+
"content": "authentication",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"27646": {
|
140 |
+
"content": "sniffing",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"28516": {
|
148 |
+
"content": "bot",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"30522": {
|
156 |
+
"content": "ransomware",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"30523": {
|
164 |
+
"content": "url",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"30524": {
|
172 |
+
"content": "phishing",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"30525": {
|
180 |
+
"content": "malware",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"30526": {
|
188 |
+
"content": "spyware",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"30527": {
|
196 |
+
"content": "botnet",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"30528": {
|
204 |
+
"content": "ddos",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"30529": {
|
212 |
+
"content": "sql injection",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"30530": {
|
220 |
+
"content": "cross-site scripting",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": true,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"30531": {
|
228 |
+
"content": "man-in-the-middle attack",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": true,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"30532": {
|
236 |
+
"content": "social engineering",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": true,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"30533": {
|
244 |
+
"content": "zero-day exploit",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": true,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"30534": {
|
252 |
+
"content": "keylogger",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": true,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": false
|
258 |
+
},
|
259 |
+
"30535": {
|
260 |
+
"content": "rootkit",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": true,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"30536": {
|
268 |
+
"content": "backdoor",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"30537": {
|
276 |
+
"content": "credential stuffing",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"30538": {
|
284 |
+
"content": "brute force attack",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"30539": {
|
292 |
+
"content": "cryptojacking",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": true,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"30540": {
|
300 |
+
"content": "data breach",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": true,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"30541": {
|
308 |
+
"content": "identity theft",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": true,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"30542": {
|
316 |
+
"content": "spoofing",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"30543": {
|
324 |
+
"content": "buffer overflow",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": true,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"30544": {
|
332 |
+
"content": "click jacking",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": true,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"30545": {
|
340 |
+
"content": "formjacking",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"30546": {
|
348 |
+
"content": "cyber espionage",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"30547": {
|
356 |
+
"content": "vishing",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": true,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"30548": {
|
364 |
+
"content": "smishing",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": true,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"30549": {
|
372 |
+
"content": "watering hole attack",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": true,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"30550": {
|
380 |
+
"content": "dns spoofing",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": true,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"30551": {
|
388 |
+
"content": "session hijacking",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"30552": {
|
396 |
+
"content": "cyber stalking",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"30553": {
|
404 |
+
"content": "eavesdropping",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": true,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"30554": {
|
412 |
+
"content": "cyber extortion",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": true,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"30555": {
|
420 |
+
"content": "typosquatting",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"30556": {
|
428 |
+
"content": "drive-by download",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": true,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"30557": {
|
436 |
+
"content": "fileless malware",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": true,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"30558": {
|
444 |
+
"content": "logic bomb",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": true,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"30559": {
|
452 |
+
"content": "pharming",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"30560": {
|
460 |
+
"content": "browser hijacking",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": true,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"30561": {
|
468 |
+
"content": "credential harvesting",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": true,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"30562": {
|
476 |
+
"content": "file injection",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": true,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"30563": {
|
484 |
+
"content": "malvertising",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": true,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"30564": {
|
492 |
+
"content": "click fraud",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"30565": {
|
500 |
+
"content": "ad fraud",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": true,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"30566": {
|
508 |
+
"content": "formgrabbing",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"30567": {
|
516 |
+
"content": "dns hijacking",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": true,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"30568": {
|
524 |
+
"content": "macroviruses",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"30569": {
|
532 |
+
"content": "packet sniffing",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"30570": {
|
540 |
+
"content": "ram scraping",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"30571": {
|
548 |
+
"content": "advanced persistent threat",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": true,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"30572": {
|
556 |
+
"content": "advanced threat protection",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": true,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"30573": {
|
564 |
+
"content": "adware",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"30574": {
|
572 |
+
"content": "anti-botnet",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": true,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"30575": {
|
580 |
+
"content": "anti-malware",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": true,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"30576": {
|
588 |
+
"content": "anti-phishing",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": true,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"30577": {
|
596 |
+
"content": "anti-virus",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": true,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"30578": {
|
604 |
+
"content": "attack vector",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": true,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"30579": {
|
612 |
+
"content": "banker trojan",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": true,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"30580": {
|
620 |
+
"content": "blacklist",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"30581": {
|
628 |
+
"content": "business continuity plan",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": true,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"30582": {
|
636 |
+
"content": "business disruption",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"30583": {
|
644 |
+
"content": "byoc",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": true,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"30584": {
|
652 |
+
"content": "byod",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": true,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"30585": {
|
660 |
+
"content": "byol",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": true,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"30586": {
|
668 |
+
"content": "captcha",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": true,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"30587": {
|
676 |
+
"content": "clickjacking",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": true,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"30588": {
|
684 |
+
"content": "clientless",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": true,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"30589": {
|
692 |
+
"content": "code injection",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": true,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"30590": {
|
700 |
+
"content": "cots",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": true,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"30591": {
|
708 |
+
"content": "critical infrastructure",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": true,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"30592": {
|
716 |
+
"content": "cyberbullying",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": true,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"30593": {
|
724 |
+
"content": "cybersecurity",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": true,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"30594": {
|
732 |
+
"content": "dark web",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": true,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"30595": {
|
740 |
+
"content": "data integrity",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": true,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"30596": {
|
748 |
+
"content": "dlp",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": true,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"30597": {
|
756 |
+
"content": "data theft",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": true,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"30598": {
|
764 |
+
"content": "decryption",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": true,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"30599": {
|
772 |
+
"content": "detection and response",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": true,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"30600": {
|
780 |
+
"content": "digital forensics",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": true,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"30601": {
|
788 |
+
"content": "digital transformation",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": true,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"30602": {
|
796 |
+
"content": "dns",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": true,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"30603": {
|
804 |
+
"content": "drive-by download attack",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": true,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"30604": {
|
812 |
+
"content": "endpoint protection",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": true,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"30605": {
|
820 |
+
"content": "fido",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": true,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"30606": {
|
828 |
+
"content": "firewall",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": true,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"30607": {
|
836 |
+
"content": "greylist",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": true,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": false
|
842 |
+
},
|
843 |
+
"30608": {
|
844 |
+
"content": "honeypot",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": true,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": false
|
850 |
+
},
|
851 |
+
"30609": {
|
852 |
+
"content": "iam",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": true,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": false
|
858 |
+
},
|
859 |
+
"30610": {
|
860 |
+
"content": "in-line network device",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"30611": {
|
868 |
+
"content": "insider threat",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": true,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": false
|
874 |
+
},
|
875 |
+
"30612": {
|
876 |
+
"content": "ips",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": true,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": false
|
882 |
+
},
|
883 |
+
"30613": {
|
884 |
+
"content": "iot",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": true,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": false
|
890 |
+
},
|
891 |
+
"30614": {
|
892 |
+
"content": "man-in-the-middle",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": true,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": false
|
898 |
+
},
|
899 |
+
"30615": {
|
900 |
+
"content": "parental controls",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": true,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": false
|
906 |
+
},
|
907 |
+
"30616": {
|
908 |
+
"content": "pen testing",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": true,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": false
|
914 |
+
},
|
915 |
+
"30617": {
|
916 |
+
"content": "pii",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": true,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": false
|
922 |
+
},
|
923 |
+
"30618": {
|
924 |
+
"content": "process hollowing",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": true,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": false
|
930 |
+
},
|
931 |
+
"30619": {
|
932 |
+
"content": "rdp",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": true,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": false
|
938 |
+
},
|
939 |
+
"30620": {
|
940 |
+
"content": "risktool",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": true,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": false
|
946 |
+
},
|
947 |
+
"30621": {
|
948 |
+
"content": "sandbox",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": true,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": false
|
954 |
+
},
|
955 |
+
"30622": {
|
956 |
+
"content": "scareware",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": true,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": false
|
962 |
+
},
|
963 |
+
"30623": {
|
964 |
+
"content": "secaas",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": true,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": false
|
970 |
+
},
|
971 |
+
"30624": {
|
972 |
+
"content": "ssl",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": true,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": false
|
978 |
+
},
|
979 |
+
"30625": {
|
980 |
+
"content": "security incident response",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": true,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": false
|
986 |
+
},
|
987 |
+
"30626": {
|
988 |
+
"content": "security perimeter",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": true,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": false
|
994 |
+
},
|
995 |
+
"30627": {
|
996 |
+
"content": "siem",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": true,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": false
|
1002 |
+
},
|
1003 |
+
"30628": {
|
1004 |
+
"content": "sim swapping",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": true,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": false
|
1010 |
+
},
|
1011 |
+
"30629": {
|
1012 |
+
"content": "soar",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": true,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": false
|
1018 |
+
},
|
1019 |
+
"30630": {
|
1020 |
+
"content": "spam",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": true,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": false
|
1026 |
+
},
|
1027 |
+
"30631": {
|
1028 |
+
"content": "spear phishing",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": true,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": false
|
1034 |
+
},
|
1035 |
+
"30632": {
|
1036 |
+
"content": "threat assessment",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": true,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": false
|
1042 |
+
},
|
1043 |
+
"30633": {
|
1044 |
+
"content": "threat hunting",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": true,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": false
|
1050 |
+
},
|
1051 |
+
"30634": {
|
1052 |
+
"content": "threat intelligence",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": true,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": false
|
1058 |
+
},
|
1059 |
+
"30635": {
|
1060 |
+
"content": "2fa",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": true,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": false
|
1066 |
+
},
|
1067 |
+
"30636": {
|
1068 |
+
"content": "vpn",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": true,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": false
|
1074 |
+
},
|
1075 |
+
"30637": {
|
1076 |
+
"content": "waf",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": true,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": false
|
1082 |
+
},
|
1083 |
+
"30638": {
|
1084 |
+
"content": "white hat",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": true,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": false
|
1090 |
+
},
|
1091 |
+
"30639": {
|
1092 |
+
"content": "black hat",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": true,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": false
|
1098 |
+
},
|
1099 |
+
"30640": {
|
1100 |
+
"content": "cybercrime",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": true,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": false
|
1106 |
+
}
|
1107 |
+
},
|
1108 |
+
"clean_up_tokenization_spaces": true,
|
1109 |
+
"cls_token": "[CLS]",
|
1110 |
+
"do_basic_tokenize": true,
|
1111 |
+
"do_lower_case": true,
|
1112 |
+
"mask_token": "[MASK]",
|
1113 |
+
"model_max_length": 512,
|
1114 |
+
"never_split": null,
|
1115 |
+
"pad_token": "[PAD]",
|
1116 |
+
"sep_token": "[SEP]",
|
1117 |
+
"strip_accents": null,
|
1118 |
+
"tokenize_chinese_chars": true,
|
1119 |
+
"tokenizer_class": "BertTokenizer",
|
1120 |
+
"unk_token": "[UNK]"
|
1121 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4709946f6d3b31dd3620992176ce6db829808b3559d72b7292e5e1680a4000d
|
3 |
+
size 4920
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|