CICIoT2023-attack-classifier

import pandas as pd
import sys
import os

# Define the attack classification mapping
attack_mapping = {
    # DDoS Attacks
    'DDoS-ICMP_Flood': 'DDoS Attacks',
    'DDoS-UDP_Flood': 'DDoS Attacks',
    'DDoS-TCP_Flood': 'DDoS Attacks',
    'DDoS-RSTFINFlood': 'DDoS Attacks',
    'DDoS-PSHACK_Flood': 'DDoS Attacks',
    'DDoS-SYN_Flood': 'DDoS Attacks',
    'DDoS-SynonymousIP_Flood': 'DDoS Attacks',
    'DDoS-ICMP_Fragmentation': 'DDoS Attacks',
    'DDoS-UDP_Fragmentation': 'DDoS Attacks',
    'DDoS-ACK_Fragmentation': 'DDoS Attacks',
    'DDoS-HTTP_Flood': 'DDoS Attacks',
    'DDoS-SlowLoris': 'DDoS Attacks',

    # DoS Attacks
    'DoS-UDP_Flood': 'DoS Attacks',
    'DoS-TCP_Flood': 'DoS Attacks',
    'DoS-SYN_Flood': 'DoS Attacks',
    'DoS-HTTP_Flood': 'DoS Attacks',

    # Mirai Botnet Attacks
    'Mirai-greeth_flood': 'Mirai Botnet Attacks',
    'Mirai-udpplain': 'Mirai Botnet Attacks',
    'Mirai-greip_flood': 'Mirai Botnet Attacks',

    # Reconnaissance
    'Recon-HostDiscovery': 'Reconnaissance',
    'Recon-OSScan': 'Reconnaissance',
    'Recon-PortScan': 'Reconnaissance',
    'Recon-PingSweep': 'Reconnaissance',

    # Web Application Attacks
    'XSS': 'Web Application Attacks',
    'SqlInjection': 'Web Application Attacks',
    'CommandInjection': 'Web Application Attacks',
    'DictionaryBruteForce': 'Web Application Attacks',
    'Uploading_Attack': 'Web Application Attacks',

    # Man-in-the-Middle Attacks
    'MITM-ArpSpoofing': 'Man-in-the-Middle Attacks',
    'DNS_Spoofing': 'Man-in-the-Middle Attacks',

    # Malware
    'BrowserHijacking': 'Malware',
    'Backdoor_Malware': 'Malware',

    # Vulnerability Assessment
    'VulnerabilityScan': 'Vulnerability Assessment',

    # Benign Traffic
    'BenignTraffic': 'Benign Traffic'
}

def reclassify_attacks(csv_path):
    try:
        # Read CSV file
        df = pd.read_csv(csv_path)

        # Get the name of the last column
        last_column = df.columns[-1]

        # Replace values in the last column using the mapping
        df[last_column] = df[last_column].map(attack_mapping)

        # Create output filename
        base_filename = os.path.splitext(csv_path)[0]
        output_filename = f"{base_filename}_reclassified.csv"

        # Save the modified dataset
        df.to_csv(output_filename, index=False)
        print(f"Successfully reclassified attacks. Saved to: {output_filename}")

        # Print summary of new classifications
        print("\nSummary of reclassified attacks:")
        print(df[last_column].value_counts())

    except Exception as e:
        print(f"Error processing file: {e}")
        sys.exit(1)

def main():
    if len(sys.argv) != 2:
        print("Usage: python3 script.py <path_to_csv_file>")
        sys.exit(1)

    csv_path = sys.argv[1]
    if not os.path.exists(csv_path):
        print(f"Error: File {csv_path} does not exist")
        sys.exit(1)

    reclassify_attacks(csv_path)

if __name__ == "__main__":
    main()