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
context-gating
calibrated-probabilities
dmarc-alignment
Eval Results (legacy)
Upload TF-IDF vocab
Browse files- tfidf_vocab.json +106 -0
tfidf_vocab.json
ADDED
|
@@ -0,0 +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 |
+
}
|