SQL INJECTION DETECTION USING RANDOM FOREST CLASSIFIER

 

SQL INJECTION DETECTION USING RANDOM FOREST CLASSIFIER

INTRODUCTION:

SQL injection, also known as SQLI, is a common attack vector that uses malicious SQL code for backend database manipulation to access information that was not intended to be displayed. This information may include any number of items, including sensitive company data, user lists or private customer details.

The impact SQL injection can have on a business is far-reaching. A successful attack may result in the unauthorized viewing of user lists, the deletion of entire tables and, in certain cases, the attacker gaining administrative rights to a database, all of which are highly detrimental to a business.

CODE 😃👇:

import pandas as pd

import numpy as np

from sklearn.model_selection import train_test_split

from sklearn.feature_extraction.text import TfidfVectorizer

from sklearn.ensemble import RandomForestClassifier

from sklearn.metrics import accuracy_score, classification_report

import pickle

# Load data

data = pd.read_csv(‘sql_injection_data.csv’)

# Check for missing values and clean if necessary

data.dropna(inplace=True)

# Split dataset into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(

data[‘query’], data[‘label’], test_size=0.2, random_state=42)

# Transform queries using TF-IDF

vectorizer = TfidfVectorizer(max_features=1000)

X_train_tfidf = vectorizer.fit_transform(X_train)

X_test_tfidf = vectorizer.transform(X_test)

# Initialize and train the classifier

model = RandomForestClassifier(n_estimators=100, random_state=42)

model.fit(X_train_tfidf, y_train)

# Evaluate on the test set

y_pred = model.predict(X_test_tfidf)

print(“Accuracy:”, accuracy_score(y_test, y_pred))

print(“Classification Report:\n”, classification_report(y_test, y_pred))

# Save model

with open(‘sql_injection_model.pkl’, ‘wb’) as model_file:

pickle.dump(model, model_file)

# Save vectorizer

with open(‘tfidf_vectorizer.pkl’, ‘wb’) as vectorizer_file:

pickle.dump(vectorizer, vectorizer_file)

def detect_sql_injection(query):

# Load model and vectorizer

with open(‘sql_injection_model.pkl’, ‘rb’) as model_file:

loaded_model = pickle.load(model_file)

with open(‘tfidf_vectorizer.pkl’, ‘rb’) as vectorizer_file:

loaded_vectorizer = pickle.load(vectorizer_file)

# Transform the query

query_tfidf = loaded_vectorizer.transform([query])

# Predict

prediction = loaded_model.predict(query_tfidf)

return “Malicious” if prediction[0] == 1 else “Benign”

# Test with a sample input

print(detect_sql_injection(“SELECT * FROM users WHERE id=1”)) # Expected output: “Benign” or “Malicious”

DATASET 😃👇

https://www.kaggle.com/datasets/syedsaqlainhussain/sql-injection-dataset

SUPPORT ME 😟

FREE C++ SKILLSHARE COURSE

https://skl.sh/3AUpE4C

FREE C SKILLSHARE COURSE

https://skl.sh/3Ynolmw

All Courses 😃👇

https://linktr.ee/Freetech2024

All Products 😃👇

https://linktr.ee/rockstararun

HP Laptop 🤩👇

https://dir.indiamart.com/impcat/hp-laptop.html?utm_source=freetech-xu1ob&utm_medium=affiliate&utm_campaign=1024&utm_content=29&mTd=1

Asus Laptop 🤩👇

https://www.indiamart.com/proddetail/24957009948.html?utm_source=freetech-xu1ob&utm_medium=affiliate&utm_campaign=1024&utm_content=43&mTd=1