train_model.py

import numpy as np
import pandas as pd
import tensorflow as tf
from sklearn.model_selection import train_test_split
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import Embedding, LSTM, Dense, Bidirectional, Dropout, Input
from tensorflow.keras.models import Model
from tensorflow.keras import regularizers
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras.optimizers import Adam

# Load and preprocess data
data = pd.read_csv("train prompt.csv", sep=',', quoting=3, encoding='ISO-8859-1', on_bad_lines='skip', engine='python')
data['label'] = data['label'].replace({'valid': 0, 'malicious': 1})

X = data['input'].values
y = data['label'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Tokenizer and padding
tokenizer = Tokenizer(num_words=5000)
tokenizer.fit_on_texts(X_train)

X_train_seq = tokenizer.texts_to_sequences(X_train)
X_test_seq = tokenizer.texts_to_sequences(X_test)

max_length = 100
X_train_pad = pad_sequences(X_train_seq, maxlen=max_length)
X_test_pad = pad_sequences(X_test_seq, maxlen=max_length)

# Model definition
input_layer = Input(shape=(max_length,))
embedding_layer = Embedding(input_dim=5000, output_dim=128, input_length=max_length)(input_layer)
x = Bidirectional(LSTM(64, return_sequences=True, dropout=0.2, kernel_regularizer=regularizers.l2(0.01)))(embedding_layer)
x = Dropout(0.3)(x)
x = Bidirectional(LSTM(64, dropout=0.2, kernel_regularizer=regularizers.l2(0.01)))(x)
malicious_output = Dense(1, activation='sigmoid')(x)

model = Model(inputs=input_layer, outputs=malicious_output)
optimizer = Adam(learning_rate=0.0001)
model.compile(optimizer=optimizer, loss='binary_crossentropy', metrics=['accuracy'])

# Training the model
early_stopping = EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)
model.fit(X_train_pad, y_train, epochs=5, batch_size=32, validation_data=(X_test_pad, y_test), callbacks=[early_stopping])

# Save the trained model
model.save("deep_learning_model.h5")
print("Model saved to deep_learning_model.h5")

if __name__ == "__main__":
    train_model()  # Ensure this calls the training function