python - 将文件转换为灰度图像

Question

我正在尝试将文件(任何文件，如 exe、apk)转换为灰度图像。我已经使用下面的代码准备了文件的二进制位。然而，我坚持将 8 位分组来表示图像中的一个像素，因此每个像素的范围是 0-255。文献表明，可以通过将恶意软件转换为灰度图像并应用CNN模型进行分类来进行分类

import cv2
import numpy
import os
import binascii

filePath = "240387329dee4f03f98a89a2feff9bf30dcba61fcf614cdac24129da54442762"
file = open(filePath, "rb")
with file:
    byte = file.read()
    hexadecimal = binascii.hexlify(byte)
    decimal = int(hexadecimal, 16)
    binary = bin(decimal)[2:].zfill(8)
    print("hex: %s, decimal: %s, binary: %s" % (hexadecimal, decimal, binary))

编辑:

我写了下面的内容，其中固定了图像的宽度。有任何反馈吗？

import cv2
import numpy
import os
import binascii
import array
import scipy.misc
#print (format(5,"b"))

filename='240387329dee4f03f98a89a2feff9bf30dcba61fcf614cdac24129da54442762';
f=open(filename,'rb');
ln = os.path.getsize(filename);
width = 500;
rem = ln%width;
a=array.array("B");
a.fromfile(f,ln-rem);
f.close;
g=numpy.reshape(a,(len(a)/width,width));
g= numpy.uint8(g);
scipy.misc.imsave('Malware.png',g);

Answer 1

您不需要将数据转换为十六进制或二进制，您所需要做的就是将二进制数据(字节序列)转换为二维数组。

问题在于，并非任何一维数组都可以 reshape 为二维数组。
例如，如果字节数为素数 = N，您将得到一个 1xN 图像(丑陋的单行或列图像)。

以下示例假设图像尺寸必须是正方形，并根据需要使用填充来完成字节数:

import numpy as np
from math import sqrt, ceil
import cv2

#Input file name (random file I found in my folder).
input_file_name = 'test_cython.cp36-win_amd64.pyd';

#Read the whole file to data
with open(input_file_name, 'rb') as binary_file:        
    data = binary_file.read()

# Data length in bytes
data_len = len(data)

# d is a verctor of data_len bytes
d = np.frombuffer(data, dtype=np.uint8)

# Assume image shape should be close to square
sqrt_len = int(ceil(sqrt(data_len)))  # Compute square toot and round up

# Requiered length in bytes.
new_len = sqrt_len*sqrt_len

# Number of bytes to pad (need to add zeros to the end of d)
pad_len = new_len - data_len

# Pad d with zeros at the end.
# padded_d = np.pad(d, (0, pad_len))
padded_d = np.hstack((d, np.zeros(pad_len, np.uint8)))

# Reshape 1D array into 2D array with sqrt_len pad_len x sqrt_len (im is going to be a Grayscale image).
im = np.reshape(padded_d, (sqrt_len, sqrt_len))

# Save image
cv2.imwrite('im.png', im)

# Display image
cv2.imshow('im' ,im)
cv2.waitKey(0)
cv2.destroyAllWindows()

结果:

<小时/>

构建可用于恢复原始文件的镜像:

如果你想获取图像，并恢复原始文件(字节相等，无填充)，则需要恢复图像中的原始数据长度。
(您也可以恢复填充的长度)。

以下实现，将原始数据长度存储在前 8 个像素中。

读取图像后，可以删除填充和存储长度，并恢复原始文件。

这是一个“编码”和“解码”示例:

import numpy as np
from math import sqrt, ceil
import cv2
import struct

#Input file name
input_file_name = 'test_cython.cp36-win_amd64.pyd';

#Read the whole file to data
with open(input_file_name, 'rb') as binary_file:        
    data = binary_file.read()

# Data length in bytes
data_len = len(data)

# d is a verctor of data_len bytes
d = np.frombuffer(data, dtype=np.uint8)

data_len_as_bytes = np.frombuffer(struct.pack("Q", data_len), dtype=np.uint8) # Convert data_len to 8 bytes

data_len = data_len + len(data_len_as_bytes) #Update length to include the 8 bytes

# Set data_len as first 8 bytes of d
d = np.hstack((data_len_as_bytes, d))

# Assume image shape should be close to square
sqrt_len = int(ceil(sqrt(data_len)))  # Compute square toot and round up

# Requiered length in bytes.
new_len = sqrt_len*sqrt_len

# Number of bytes to pad (need to add zeros to the end of d)
pad_len = new_len - data_len

# Pad d with zeros at the end.
# padded_d = np.pad(d, (0, pad_len))
padded_d = np.hstack((d, np.zeros(pad_len, np.uint8)))

# Reshape 1D array into 2D array with sqrt_len pad_len x sqrt_len (im is going to be a Grayscale image).
im = np.reshape(padded_d, (sqrt_len, sqrt_len))

# Save image
cv2.imwrite('im.png', im)

# Display image
#cv2.imshow('im' ,im)
#cv2.waitKey(0)
#cv2.destroyAllWindows()


# Restore original data:
##################################
input_file_name = 'test.bin';  #Output file name

im = cv2.imread('im.png', cv2.IMREAD_GRAYSCALE)

# Convert 2D to 1D
padded_d = im.flatten()

# Get original length
data_len_as_bytes = padded_d[0:8]

orig_data_len = struct.unpack("Q", data_len_as_bytes.tobytes())

# Crop the original data bytes (without the padding).
data = padded_d[8:8+orig_data_len[0]]

#Write d whole file to binary file
with open(input_file_name, 'wb') as binary_file:
    binary_file.write(data)

现在您可以将任何(小)文件作为图像上传到 Stack Overflow，并让其他人恢复您的文件。