Kanishka Sharma

17 papers C 2Journal 7Unranked 8
YearRankTypeTitle / Venue / Authors
2025 J jnl
CoRR
Jerrin Thomas Panachakel, G. Pradeep Kumar, Suryaa Seran, Kanishka Sharma, Ramakrishnan Angarai Ganesan
2024 J jnl
CoRR
Loai Danial, Kanishka Sharma, Shahar Kvatinsky
2024 J jnl
NeuroImage
G. Pradeep Kumar, Rajanikant Panda, Kanishka Sharma, A. Adarsh, Jitka Annen, Charlotte Martial, Marie Élisabeth Faymonville, Steven Laureys, Corine Sombrun, Ramakrishnan Angarai Ganesan, Audrey Vanhaudenhuyse, Olivia Gosseries
2023 conf
ICCCNT
Kanishka Sharma, Avneet Kaur, Srabasti Ghosh, Anshika Abrol
2022 conf
BIOSIG
G. Pradeep Kumar, Utsav Dutta, Kanishka Sharma, Ramakrishnan Angarai Ganesan
2022 conf
MeMeA
A. S. Anusha, A. G. Ramakrishnan, A. Adarsh, Kanishka Sharma, G. Pradeep Kumar
2022 J jnl
CoRR
G. Pradeep Kumar, Utsav Dutta, Kanishka Sharma, Ramakrishnan Angarai Ganesan
2021 C conf
TENCON
Jerrin Thomas Panachakel, G. Pradeep Kumar, A. G. Ramakrishnan, Kanishka Sharma
2021 conf
EMBC
Jerrin Thomas Panachakel, Kanishka Sharma, Anusha A. S, A. G. Ramakrishnan
2021 conf
EMBC
G. Pradeep Kumar, Kanishka Sharma, A. G. Ramakrishnan, A. Adarsh
2020 C conf
ISCAS
Loai Danial, Kanishka Sharma, Shahar Kvatinsky
2020 J jnl
CoRR
Jerrin Thomas Panachakel, Nandagopal Netrakanti Vinayak, Maanvi Nunna, A. G. Ramakrishnan, Kanishka Sharma
2019 conf
BioCAS
Loai Danial, Kanishka Sharma, Shivansh Dwivedi, Shahar Kvatinsky
2018 J jnl
Brain Connect.
Kanishka Sharma, Richa Trivedi, Sushil Chandra, Prabhjot Kaur, Pawan Kumar, Kavita Singh, Ashok K. Dubey, Subash Khushu
2015 J jnl
CoRR
Kanishka Sharma, Loïc Peter, Christian Rupprecht, Anna Caroli, Lichao Wang, Andrea Remuzzi, Maximilian Baust, Nassir Navab
2013 conf
MICCAI (1)
Philipp Matthies, Kanishka Sharma, Asli Okur, José Gardiazabal, Jakob Vogel, Tobias Lasser, Nassir Navab
2013 conf
MICCAI (1)
Wolfgang Wein, Alexander Ladikos, Bernhard Fuerst, Amit Shah, Kanishka Sharma, Nassir Navab
redb/utils/sort_files_by_type.py
← Index redb/utils/sort_files_by_type.py python
import os
import sys
from collections import defaultdict
import tempfile
from magika import Magika
import py7zr
import pyzipper
import shutil

"""
This script is used to sort files by their type. 
It reads all the files in the provided directory and splits them into different 
directories based on their type. Mainly, it classifies the files into the following types:
- PE Binaries
- Mach-O Binaries
- ELF Binaries
- APK 
- Other Files

It outputs the count of files for each file extension and file type.

Command line example:
nohup python3 sort_files_by_type.py /mnt/samples/consilience/malware/vx-bazaar-expanded/Bazaar.2020.12 \
    /mnt/samples/consilience/malware/_sorted_samples/vx-bazaar/2020/ > \
    /mnt/samples/consilience/malware/ops-logs/20241014-SORT_FILES-bazaar_2020.12.output.log 2>&1 &
"""


def process_zip_file(filepath):
    print(f"[INFO] - Processing zip file: {filepath}")
    with tempfile.TemporaryDirectory() as temp_dir:
        try:
            with pyzipper.AESZipFile(filepath) as zf:
                zf.pwd = b"infected"
                filename = zf.namelist()[0]
                zf.extractall(temp_dir)
                extracted_zip_path = os.path.join(temp_dir, filename)
                return process_binary_file(extracted_zip_path)
        except Exception as e:
            print(f"[ERR] - Error processing zip file {filepath}: {str(e)}")
            return None


def process_7z_file(filepath):
    print(f"[INFO] - Processing 7z file: {filepath}")
    with tempfile.TemporaryDirectory() as temp_dir:
        try:
            with py7zr.SevenZipFile(filepath, mode="r", password="infected") as z:
                z.extractall(path=temp_dir)
                for root, _, files in os.walk(temp_dir):
                    for file in files:
                        extracted_file_path = os.path.join(root, file)
                        return process_binary_file(extracted_file_path)
        except Exception as e:
            print(f"[ERR] - Error processing 7z file {filepath}: {str(e)}")
            return None


def process_binary_file(filepath):
    print(f"[INFO] - Processing binary file: {filepath}")
    try:
        with open(filepath, "rb") as f:
            data = f.read(512 * 1024)  # 512KB
        return Magika().identify_bytes(data).output.ct_label
    except Exception as e:
        print(f"[ERR] - Error processing binary file {filepath}: {str(e)}")
        return "ERROR"


def count_file_extensions(path, dest_dir):
    # A defaultdict to store file extension counts
    extension_count = defaultdict(int)
    filetype_count = defaultdict(int)
    tot_files = 0

    # Walk through the directory
    for root, dirs, files in os.walk(path):
        for file in files:
            if file.startswith("."):
                continue

            tot_files += 1
            # Split the file extension from the file name
            _, ext = os.path.splitext(file)
            ext = ext.lower()

            # Count the extensions
            extension_count[ext] += 1
            filepath = os.path.join(root, file)
            filetype = ""

            if ext == ".7z":
                filetype = process_7z_file(filepath)
            elif ext == ".zip":
                filetype = process_zip_file(filepath)
            else:
                filetype = process_binary_file(filepath)

            filetype_count[filetype] += 1

            if filetype == "pebin":
                dest = os.path.join(dest_dir, "pebin")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            elif filetype == "macho":
                dest = os.path.join(dest_dir, "macho")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            elif filetype == "elf":
                dest = os.path.join(dest_dir, "elf")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            elif filetype == "apk":
                dest = os.path.join(dest_dir, "apk")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            else:
                dest = os.path.join(dest_dir, "other")
                os.makedirs(dest, exist_ok=True)
                shutil.copy2(filepath, os.path.join(dest, file))
            print(f"[STATUS] - Progres: {tot_files}/{len(files)} files processed")

    # Print the results
    # print("- File Extension Statistics:")
    # for ext, count in extension_count.items():
    #     if ext:  # To exclude files with no extension
    #         print(f"\t{ext}: {count} files")

    # if "" in extension_count:
    #     print(f'\t{extension_count[""]} files with no extension')

    print(f"- Total Number of Files: {tot_files}")
    print("\n- File Type Statistics:")
    for filetype, count in sorted(filetype_count.items()):
        print(f"\t{filetype:<15}{count:>8}")


if __name__ == "__main__":
    # Check if the path was passed as a command-line argument
    if len(sys.argv) != 3:
        print("Usage: python3 script.py <input_path> <dest_dir>")
        sys.exit(1)

    # Get the path from the command-line arguments
    input_path = sys.argv[1]
    dest_dir = sys.argv[2]

    # Check if the provided path is valid
    if not os.path.isdir(input_path):
        print(f"The path '{input_path}' is not a valid directory.")
        sys.exit(1)

    # Call the function to count file extensions
    count_file_extensions(input_path, dest_dir)