File size: 2,915 Bytes
df39992 b2a603e df39992 f686213 df39992 b2a603e df39992 f686213 df39992 |
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 |
import streamlit as st
import pandas as pd
import joblib
import pickle
import numpy as np
# Load model and preprocessing artifacts
model = joblib.load("ensemble_model.pkl")
with open("features_to_drop.pkl", "rb") as f:
features_to_drop = pickle.load(f)
# Map of numerical predictions to attack category strings
label_map = {
0: 'Fuzzers',
1: 'Fuzzers',
2: 'Reconnaissance',
3: 'Shellcode',
4: 'Analysis',
5: 'Backdoor',
6: 'Backdoors',
7: 'DoS',
8: 'Exploits',
9: 'Generic',
10: 'Reconnaissance',
11: 'Shellcode',
12: 'Worms',
13: 'normal'
}
# Column names from the raw 49-column dataset (before feature engineering)
raw_columns = [
'srcip', 'sport', 'dstip', 'dsport', 'proto', 'state', 'dur', 'sbytes', 'dbytes',
'sttl', 'dttl', 'sloss', 'dloss', 'service', 'Sload', 'Dload', 'Spkts', 'Dpkts',
'swin', 'dwin', 'stcpb', 'dtcpb', 'smeansz', 'dmeansz', 'trans_depth', 'res_bdy_len',
'Sjit', 'Djit', 'Stime', 'Ltime', 'Sintpkt', 'Dintpkt', 'tcprtt', 'synack', 'ackdat',
'is_sm_ips_ports', 'ct_state_ttl', 'ct_flw_http_mthd', 'is_ftp_login', 'ct_ftp_cmd',
'ct_srv_src', 'ct_srv_dst', 'ct_dst_ltm', 'ct_src_ ltm', 'ct_src_dport_ltm',
'ct_dst_sport_ltm', 'ct_dst_src_ltm', 'attack_cat', 'Label'
]
# Function to preprocess a single input row
def preprocess_input(row_values):
if len(row_values) != 49:
raise ValueError(f"❌ Expected 49 values, but got {len(row_values)}.")
# Create DataFrame from input
input_df = pd.DataFrame([row_values], columns=raw_columns)
# Convert all columns to numeric
input_df = input_df.apply(pd.to_numeric, errors='coerce')
# Feature engineering
input_df['duration'] = input_df['Ltime'] - input_df['Stime']
input_df['byte_ratio'] = input_df['sbytes'] / (input_df['dbytes'] + 1)
input_df['pkt_ratio'] = input_df['Spkts'] / (input_df['Dpkts'] + 1)
# ✅ Fix: convert features_to_drop to list before adding with another list
input_df = input_df.drop(columns=list(features_to_drop) + ['attack_cat', 'Label'], errors='ignore')
return input_df
# Streamlit UI
st.title("🔍 Anomaly Detection In Network Traffic")
st.markdown("Paste a **single row** of raw features from the dataset (49 values, tab-separated):")
user_input = st.text_area("Input Row", height=150)
if st.button("Predict"):
try:
# Parse the input
values = user_input.strip().split("\t")
# Preprocess the input row
processed_df = preprocess_input(values)
# Predict using the preprocessed data
predicted_label = model.predict(processed_df)[0]
# Map the prediction to string label
predicted_category = label_map.get(predicted_label, "Unknown")
st.success(f"✅ Predicted Attack Category: **{predicted_category}**")
except Exception as e:
st.error(f"❌ Error processing input: {e}")
|