Tailbone

这里本来想修改为Intel的另一条指令aesdec,没想到兜了好大的圈子。

我们可以看到对于单轮运算,使用aesdec是逆不过来的。

所以我们必须对于每一步运算进行如下运算

xor_key
inv_mix_columns
inv_shift_rows
inv_sub_bytes

参考github上AES的实现,写出如下脚本。

import binascii

inv_s_box = (
    0x52, 0x09, 0x6A, 0xD5, 0x30, 0x36, 0xA5, 0x38, 0xBF, 0x40, 0xA3, 0x9E, 0x81, 0xF3, 0xD7, 0xFB,
    0x7C, 0xE3, 0x39, 0x82, 0x9B, 0x2F, 0xFF, 0x87, 0x34, 0x8E, 0x43, 0x44, 0xC4, 0xDE, 0xE9, 0xCB,
    0x54, 0x7B, 0x94, 0x32, 0xA6, 0xC2, 0x23, 0x3D, 0xEE, 0x4C, 0x95, 0x0B, 0x42, 0xFA, 0xC3, 0x4E,
    0x08, 0x2E, 0xA1, 0x66, 0x28, 0xD9, 0x24, 0xB2, 0x76, 0x5B, 0xA2, 0x49, 0x6D, 0x8B, 0xD1, 0x25,
    0x72, 0xF8, 0xF6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xD4, 0xA4, 0x5C, 0xCC, 0x5D, 0x65, 0xB6, 0x92,
    0x6C, 0x70, 0x48, 0x50, 0xFD, 0xED, 0xB9, 0xDA, 0x5E, 0x15, 0x46, 0x57, 0xA7, 0x8D, 0x9D, 0x84,
    0x90, 0xD8, 0xAB, 0x00, 0x8C, 0xBC, 0xD3, 0x0A, 0xF7, 0xE4, 0x58, 0x05, 0xB8, 0xB3, 0x45, 0x06,
    0xD0, 0x2C, 0x1E, 0x8F, 0xCA, 0x3F, 0x0F, 0x02, 0xC1, 0xAF, 0xBD, 0x03, 0x01, 0x13, 0x8A, 0x6B,
    0x3A, 0x91, 0x11, 0x41, 0x4F, 0x67, 0xDC, 0xEA, 0x97, 0xF2, 0xCF, 0xCE, 0xF0, 0xB4, 0xE6, 0x73,
    0x96, 0xAC, 0x74, 0x22, 0xE7, 0xAD, 0x35, 0x85, 0xE2, 0xF9, 0x37, 0xE8, 0x1C, 0x75, 0xDF, 0x6E,
    0x47, 0xF1, 0x1A, 0x71, 0x1D, 0x29, 0xC5, 0x89, 0x6F, 0xB7, 0x62, 0x0E, 0xAA, 0x18, 0xBE, 0x1B,
    0xFC, 0x56, 0x3E, 0x4B, 0xC6, 0xD2, 0x79, 0x20, 0x9A, 0xDB, 0xC0, 0xFE, 0x78, 0xCD, 0x5A, 0xF4,
    0x1F, 0xDD, 0xA8, 0x33, 0x88, 0x07, 0xC7, 0x31, 0xB1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xEC, 0x5F,
    0x60, 0x51, 0x7F, 0xA9, 0x19, 0xB5, 0x4A, 0x0D, 0x2D, 0xE5, 0x7A, 0x9F, 0x93, 0xC9, 0x9C, 0xEF,
    0xA0, 0xE0, 0x3B, 0x4D, 0xAE, 0x2A, 0xF5, 0xB0, 0xC8, 0xEB, 0xBB, 0x3C, 0x83, 0x53, 0x99, 0x61,
    0x17, 0x2B, 0x04, 0x7E, 0xBA, 0x77, 0xD6, 0x26, 0xE1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0C, 0x7D,
)

def inv_sub_bytes(s):
    for i in range(4):
        for j in range(4):
            s[i][j] = inv_s_box[s[i][j]]

def add_round_key(s, k):
    for i in range(4):
        for j in range(4):
            s[i][j] ^= k[i][j]

def inv_shift_rows(s):
    s[0][1], s[1][1], s[2][1], s[3][1] = s[3][1], s[0][1], s[1][1], s[2][1]
    s[0][2], s[1][2], s[2][2], s[3][2] = s[2][2], s[3][2], s[0][2], s[1][2]
    s[0][3], s[1][3], s[2][3], s[3][3] = s[1][3], s[2][3], s[3][3], s[0][3]

xtime = lambda a: (((a << 1) ^ 0x1B) & 0xFF) if (a & 0x80) else (a << 1)

def mix_single_column(a):
    # see Sec 4.1.2 in The Design of Rijndael
    t = a[0] ^ a[1] ^ a[2] ^ a[3]
    u = a[0]
    a[0] ^= t ^ xtime(a[0] ^ a[1])
    a[1] ^= t ^ xtime(a[1] ^ a[2])
    a[2] ^= t ^ xtime(a[2] ^ a[3])
    a[3] ^= t ^ xtime(a[3] ^ u)


def mix_columns(s):
    for i in range(4):
        mix_single_column(s[i])

def inv_mix_columns(s):
    # see Sec 4.1.3 in The Design of Rijndael
    for i in range(4):
        u = xtime(xtime(s[i][0] ^ s[i][2]))
        v = xtime(xtime(s[i][1] ^ s[i][3]))
        s[i][0] ^= u
        s[i][1] ^= v
        s[i][2] ^= u
        s[i][3] ^= v
    mix_columns(s)

def bytes2matrix(text):
    """ Converts a 16-byte array into a 4x4 matrix.  """
    return [list(text[i:i+4]) for i in range(0, len(text), 4)]

def matrix2bytes(matrix):
    """ Converts a 4x4 matrix into a 16-byte array.  """
    return bytes(sum(matrix, []))

def decrypt_block(ciphertext,key):
    cipher_state = bytes2matrix(ciphertext)
    key = bytes2matrix(key)
    add_round_key(cipher_state, key)
    inv_mix_columns(cipher_state)
    inv_shift_rows(cipher_state)
    inv_sub_bytes(cipher_state)
    return matrix2bytes(cipher_state)

datas = ['D1E8FCB9AC4BDF4948BA54E26A282F9A', '7AEB61B0A637139CD0DCE7DBDB0636F7']
keys = ['31ED4989D15E4889E24883E4F0505449', 'C7C00007400048C7C19006400048C7C7', '48064000E8A7FFFFFFF4660F1F440000', 'B85710600055482D501060004883F80E', '4889E5761BB8000000004885C074115D', 'BF50106000FFE0660F1F840000000000', '5DC30F1F4000662E0F1F840000000000', 'BE50106000554881EE5010600048C1FE', '034889E54889F048C1E83F4801C648D1']
if __name__ == "__main__":
    flag = ''
    for i in range(2):
        ciphertext = binascii.unhexlify(datas[i])
        for j in range(3,-1,-1):
            key = binascii.unhexlify(keys[j+4*i])
            ciphertext = decrypt_block(ciphertext,key)
        flag += ciphertext.decode("utf-8")
    print(flag)

从这道题目学到了xmm 128位寄存器,每个寄存器保存16bytes,不需要考虑小端序。
我们使用idapython dump keys的脚本就可以这样写

key_address = 0x400530
data_address = 0x400840
keys = []
for i in range(0,0x90,0x10):
    key = []
    for j in range(0x10):
        key.append(get_wide_byte(key_address+i+j))
    keys.append("".join([hex(x)[2:].upper().zfill(2) for x in key]))
datas = []
for i in range(0,0x20,0x10):
    data = []
    for j in range(0x10):
        data.append(get_wide_byte(data_address+i+j))
    datas.append("".join([hex(x)[2:].upper().zfill(2) for x in data]))
print datas
print keys

参考链接:

https://github.com/boppreh/aes

https://software.intel.com/en-us/articles/intel-advanced-encryption-standard-instructions-aes-ni/

https://www.cosic.esat.kuleuven.be/ecrypt/AESday/slides/Use_of_the_AES_Instruction_Set.pdf

hideandseek

这是一道不断smc的程序,技巧就是设置input所在内存位置访问断点,我们不断使用F9,查看访问input的代码,每个函数对应一个方程。
解出所有方程,拿到flag。