stegano_lsb.py

#!/usr/bin/env python3

""" Wavデータに対して、LSBにメッセージを隠す. """

# Copyright (C) 2020 Akira TAMAMORI

# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.


import stegano.tools as tools
import soundfile as sf
import numpy as np
from scipy.io.wavfile import write as wav_write
from scipy.io.wavfile import read as wav_read


def hide(infile: str,   # 元のwav
         outfile: str,  # メッセージを隠したwav
         message: str,  # 隠すメッセージ
         encoding: str = "UTF-8"):
    """ 最下位ビット(LSB)にメッセージを隠す """

    _, wav_data = wav_read(infile)
    with sf.SoundFile(infile) as wav_file:
        num_channel = wav_file.channels
        num_frame = wav_file.frames
        samplerate = wav_file.samplerate

        # scipyのwav_readでは、dataのshapeが(num_frame, num_channel)
        # →vectorへと形状変換する
        if num_channel > 1:
            wav_data = np.reshape(wav_data, [num_channel * num_frame, -1])

    wav_data = wav_data.copy()  # in order to overwrite
    wav_data = wav_data.astype('int16')  # short int型にキャスト

    # 例えば 「12:Hello, World!」のように、メッセージ長と区切り文字を作る
    # →メッセージの「ヘッダ」を付与するイメージ
    message = str(len(message)) + ":" + str(message)

    # メッセージを0と1からなる「文字列」に加工
    # →各文字のasciiコードを２進表現した「文字列」を１つの文字列に連結
    message_bits = "".join(tools.a2bits_list(message, encoding))
    len_message_bits = len(message_bits)

    index = 0
    for _ in range(num_frame):
        for _ in range(num_channel):

            if index + 1 <= len_message_bits:
                # 最下位ビットにメッセージを隠す
                wav_data[index] = tools.setlsb(wav_data[index],
                                               message_bits[index])
                index = index + 1

    # vectorを元のshapeに戻す
    if num_channel > 1:
        wav_data = np.reshape(wav_data, [num_frame, num_channel])

    wav_write(outfile, samplerate, wav_data)


def reveal(infile: str,  # LSBにメッセージが隠されたwav
           encoding: str = "UTF-8"):
    """ LSBに隠したメッセージを取り出す """

    _, wav_data = wav_read(infile)
    with sf.SoundFile(infile) as wav_file:
        num_channel = wav_file.channels
        num_frame = wav_file.frames
        if num_channel > 1:
            wav_data = np.reshape(wav_data, [num_channel * num_frame, -1])

    ascii_code, count = 0, 0
    message_chars = []
    message_length = None
    index = 0
    hidden_message = None
    for _ in range(num_frame):
        for _ in range(num_channel):

            # 最下位ビットを取得して
            # →次に来るビットのため、あらかじめビットシフトして「空けておく」
            ascii_code += (wav_data[index] & 1) \
                << (tools.ENCODINGS[encoding] - 1 - count)
            count += 1
            index += 1

            # 8回ビットシフトしたらasciiに戻す（1文字は8bitなので）
            # ←tools.ENCODINGS[encoding]の戻り値は8
            if count == tools.ENCODINGS[encoding]:
                # chr() は asciiコードをascii文字に戻す関数
                message_chars.append(chr(ascii_code))
                ascii_code, count = 0, 0  # カウントをリセット

                # 末尾が区切り文字 かつ メッセージ未取得
                if message_chars[-1] == ":" and message_length is None:
                    try:
                        # 区切り文字前の数字からメッセージの長さを確定
                        message_length = int("".join(message_chars[:-1]))
                    except Exception:
                        pass

            # 区切り文字 ':' に続く文字列を隠しメッセージとして取得
            if (len(message_chars) -
                    len(str(message_length)) - 1) == message_length:

                # 区切り文字以降の文字を連結
                hidden_message = "".join(message_chars)[
                    len(str(message_length)) + 1:]

    return hidden_message


def main():
    """main routine"""

    host_wav = './input/host.wav'  # 元の音
    stego_wav = './output/stegano.wav'  # メッセージを隠した音

    # LSB にメッセージを隠す
    hide(infile=host_wav, outfile=stego_wav,
         message="Hello, World!")

    # 隠したメッセージを取り出す
    message = reveal(stego_wav)

    print(f"Hidden message is \"{message}\"")


if __name__ == '__main__':
    main()