Hugging Face's logo

SamSec007
/
phishbyte

Text Classification
Safetensors
PyTorch
English
phishbyte
phishing-detection
email-security
cybersecurity
security
from-scratch
no-pretrained-weights
cascading-inference
lightweight
explainable-ai
nlp
phishing
spam-detection
malware-detection
threat-detection
email-classification
feature-engineering
interpretable-ml
tfidf
residual-network
cross-signal-fusion
lexical-analysis
calibrated-probabilities
Eval Results (legacy)
Model card Files
xet
 Community
SamSec007 commited on
Commit
5b8a3a4
·
verified ·
1 Parent(s): 6cd1fa0

Upload TF-IDF vocab

Browse files
Files changed (1) hide show
  1. tfidf_vocab.json +89 -89
tfidf_vocab.json CHANGED
@@ -1,106 +1,106 @@
1
  {
2
  "vocab": [
3
- "cnn",
4
- "com",
5
- "python",
6
  "replica",
7
- "enron",
8
  "watches",
9
- "ect",
10
- "http",
11
  "index",
12
- "org",
13
- "video",
14
- "html",
15
- "xls",
 
 
16
  "here",
17
- "subject",
18
- "attached",
19
- "alert",
20
- "www",
21
  "file",
22
- "dev",
23
- "hou",
24
- "wrote",
25
- "rolex",
26
  "thanks",
27
- "list",
28
- "click",
29
- "email",
30
- "love",
31
- "alerts",
32
- "spamassassin",
33
- "custom",
34
- "life",
35
  "watch",
 
 
 
 
 
 
 
 
 
 
36
  "men",
 
 
37
  "classics",
38
- "vince",
 
 
 
 
 
 
 
 
39
  "health",
40
- "mailman",
41
- "account",
42
- "livefilestore",
43
- "money",
44
- "hpl",
45
- "font",
46
- "schedules",
47
  "date",
48
- "perl",
49
- "partners",
50
- "linux",
51
- "know",
52
- "top"
53
  ],
54
  "idf": {
55
- "cnn": 3.859323,
56
- "com": 1.505416,
57
- "python": 3.981779,
58
- "replica": 4.587008,
59
- "enron": 3.511213,
60
- "watches": 4.463505,
61
- "ect": 4.220619,
62
- "http": 1.729441,
63
- "index": 3.723175,
64
- "org": 2.589699,
65
- "video": 3.918011,
66
- "html": 3.087423,
67
- "xls": 5.994789,
68
- "here": 2.47944,
69
- "subject": 1.33207,
70
- "attached": 3.990582,
71
- "alert": 4.660815,
72
- "www": 2.405916,
73
- "file": 3.593676,
74
- "dev": 4.417054,
75
- "hou": 4.33319,
76
- "wrote": 3.084136,
77
- "rolex": 4.875124,
78
- "thanks": 3.033234,
79
- "list": 2.662902,
80
- "click": 3.134414,
81
- "email": 2.487115,
82
- "love": 3.723541,
83
- "alerts": 4.856207,
84
- "spamassassin": 3.7029,
85
- "custom": 4.6754,
86
- "life": 3.362084,
87
- "watch": 4.251155,
88
- "men": 4.462355,
89
- "classics": 4.983833,
90
- "vince": 4.105948,
91
- "health": 3.951223,
92
- "mailman": 3.326527,
93
- "account": 3.614127,
94
- "livefilestore": 5.818098,
95
- "money": 3.457356,
96
- "hpl": 5.616887,
97
- "font": 5.026674,
98
- "schedules": 5.51092,
99
- "date": 3.064163,
100
- "perl": 4.849979,
101
- "partners": 4.072717,
102
- "linux": 4.128458,
103
- "know": 2.8689,
104
- "top": 3.447036
105
  }
106
  }
 
1
  {
2
  "vocab": [
 
 
 
3
  "replica",
4
+ "python",
5
  "watches",
6
+ "cnn",
 
7
  "index",
8
+ "livefilestore",
9
+ "enron",
10
+ "pills",
11
+ "perl",
12
+ "wrote",
13
+ "list",
14
  "here",
 
 
 
 
15
  "file",
16
+ "escapelong",
 
 
 
17
  "thanks",
18
+ "price",
 
 
 
 
 
 
 
19
  "watch",
20
+ "rolex",
21
+ "life",
22
+ "love",
23
+ "mailman",
24
+ "stat",
25
+ "ethz",
26
+ "bay",
27
+ "quality",
28
+ "posting",
29
+ "click",
30
  "men",
31
+ "schedules",
32
+ "attached",
33
  "classics",
34
+ "online",
35
+ "guide",
36
+ "ect",
37
+ "buy",
38
+ "listinfo",
39
+ "code",
40
+ "video",
41
+ "sent",
42
+ "alert",
43
  "health",
44
+ "dev",
45
+ "help",
46
+ "mailing",
47
+ "please",
 
 
 
48
  "date",
49
+ "data",
50
+ "target",
51
+ "hourahead",
52
+ "best"
 
53
  ],
54
  "idf": {
55
+ "replica": 4.937652,
56
+ "python": 4.444293,
57
+ "watches": 4.789794,
58
+ "cnn": 4.362797,
59
+ "index": 4.181594,
60
+ "livefilestore": 6.312717,
61
+ "enron": 3.703523,
62
+ "pills": 5.278147,
63
+ "perl": 4.317696,
64
+ "wrote": 2.875187,
65
+ "list": 2.593572,
66
+ "here": 2.509424,
67
+ "file": 3.363717,
68
+ "escapelong": 4.368936,
69
+ "thanks": 2.887331,
70
+ "price": 3.523213,
71
+ "watch": 4.216665,
72
+ "rolex": 5.193097,
73
+ "life": 3.648976,
74
+ "love": 4.101438,
75
+ "mailman": 3.130467,
76
+ "stat": 4.005099,
77
+ "ethz": 4.039423,
78
+ "bay": 5.936061,
79
+ "quality": 4.042238,
80
+ "posting": 3.92025,
81
+ "click": 3.277176,
82
+ "men": 4.424445,
83
+ "schedules": 5.260086,
84
+ "attached": 4.12807,
85
+ "classics": 5.521181,
86
+ "online": 3.783916,
87
+ "guide": 3.861883,
88
+ "ect": 5.154697,
89
+ "buy": 4.014442,
90
+ "listinfo": 3.082393,
91
+ "code": 3.259528,
92
+ "video": 4.366216,
93
+ "sent": 3.118425,
94
+ "alert": 4.402654,
95
+ "health": 4.048149,
96
+ "dev": 4.807262,
97
+ "help": 2.785651,
98
+ "mailing": 3.010985,
99
+ "please": 2.305519,
100
+ "date": 3.294857,
101
+ "data": 3.618996,
102
+ "target": 4.537779,
103
+ "hourahead": 5.381485,
104
+ "best": 3.196797
105
  }
106
  }