Text Classification
Transformers
Safetensors
English
distilbert
cybersecurity
xss
security
web
payload-detection
web-security
Instructions to use kd7979148/XSS_Payload_Detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kd7979148/XSS_Payload_Detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="kd7979148/XSS_Payload_Detector")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("kd7979148/XSS_Payload_Detector") model = AutoModelForSequenceClassification.from_pretrained("kd7979148/XSS_Payload_Detector") - Notebooks
- Google Colab
- Kaggle
File size: 4,771 Bytes
afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 afd9f5c 4f77521 | 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 | # -*- coding: utf-8 -*-
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
from urllib.parse import (
urlparse,
parse_qs,
unquote
)
#################################################
# model path
#################################################
model_path = "xss_detect_trained"
#################################################
# URL existence
#################################################
def is_url(text):
return text.startswith("http://") or text.startswith("https://")
#################################################
# URL에서 parameter value
#################################################
def extract_url_payload(url):
try:
parsed = urlparse(url)
# query parameter
params = parse_qs(parsed.query)
extracted = []
for key, values in params.items():
for value in values:
# URL decode
decoded = unquote(value)
extracted.append(decoded)
# use path when no parameter
if not extracted:
return parsed.path
# combine multiple parameters
return " ".join(extracted)
except:
return url
#################################################
# check
#################################################
def contains_suspicious_code(text):
suspicious_patterns = [
# HTML / JS
"<",
">",
"script",
"javascript:",
"onerror",
"onclick",
"onload",
"iframe",
"svg",
# JS
"eval(",
"alert(",
"prompt(",
"confirm(",
"document.cookie",
"document.domain",
"window.location",
# bypass
"constructor",
"fromcharcode",
"\\x",
"%3c",
"%3e",
"&#",
"base64",
"atob(",
#
"srcdoc",
"data:text/html",
"vbscript:",
"expression("
]
text_lower = text.lower()
for pattern in suspicious_patterns:
if pattern in text_lower:
return True
return False
#################################################
# load
#################################################
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)
device = torch.device("cpu")
model.to(device)
model.eval()
#################################################
# label
#################################################
labels = {
0: "NORMAL",
1: "XSS"
}
#################################################
# test
#################################################
print("\n Test Start (type exit to end)\n")
while True:
text = input("input: ")
if text.lower() == "exit":
break
#################################################
# basic
#################################################
target_text = text
#################################################
# URL
#################################################
if is_url(text):
target_text = extract_url_payload(text)
print(f"[extracted parameter]: {target_text}")
#################################################
# NORMAL when no suspicious code
#################################################
if not contains_suspicious_code(target_text):
print("result: NORMAL")
print("Reliability: heuristic\n")
continue
#################################################
# tokenize
#################################################
MAX_INPUT_LENGTH = 2000
if len(target_text) > MAX_INPUT_LENGTH:
print("Input Length Exceeded\n")
continue
inputs = tokenizer(
target_text,
return_tensors="pt",
truncation=True,
padding=True,
max_length=128
).to(device)
#################################################
#
#################################################
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits
probs = torch.softmax(logits, dim=1)
confidence, pred = torch.max(probs, dim=1)
pred = pred.item()
confidence = confidence.item()
label = labels[pred]
#################################################
# result
#################################################
print(f"result: {label}")
print(f"Reliability: {confidence:.4f}\n")
|