AES

AES

• 是一种对称加密算法，加密再解密就是明文

步骤：

1.字节变换：状态矩阵中的元素按照下面的方式映射为一个新的字节：把该字节的高4位作为行值，低4位作为列值，取出S盒或者逆S盒中对应的行的元素作为输出。例如，加密时，输出的字节S1为0x12,则查S盒的第0x01行和0x02列，得到值0xc9,然后替换S1原有的0x12为0xc9。状态矩阵经字节代换后的图如下

逆：用逆s盒
2.行移位

行移位的逆变换：行移位的逆变换是将状态矩阵中的每一行执行相反的移位操作，例如AES-128中，状态矩阵的第0行右移0字节，第1行右移1字节，第2行右移2字节，第3行右移3字节。
3.列混合
复杂的矩阵变换，通过矩阵相乘来实现的，经行移位后的状态矩阵与固定的矩阵相乘，得到混淆后的状态矩阵（太难了不会

4.轮密钥加
轮密钥加是将128位轮密钥Ki同状态矩阵中的数据进行逐位异或操作，其中，密钥Ki中每个字W[4i],W[4i+1],W[4i+2],W[4i+3]为32位比特字，包含4个字节，他们的生成算法下面在下面介绍。轮密钥加过程可以看成是字逐位异或的结果，也可以看成字节级别或者位级别的操作。也就是说，可以看成S0 S1 S2 S3 组成的32位字与W[4i]的异或运算。

轮密钥加的逆运算同正向的轮密钥加运算完全一致，这是因为异或的逆操作是其自身。轮密钥加非常简单，但却能够影响S数组中的每一位。
（接下来是对密钥）
AES首先将初始密钥输入到一个4*4的状态矩阵中
T是一个有点复杂的函数。
函数T由3部分组成：字循环、字节代换和轮常量异或，这3部分的作用分别如下。
a.字循环：将1个字中的4个字节循环左移1个字节。即将输入字[b0, b1, b2, b3]变换成[b1,b2,b3,b0]。
b.字节代换：对字循环的结果使用S盒进行字节代换。
c.轮常量异或：将前两步的结果同轮常量Rcon[j]进行异或，其中j表示轮数。
轮常量Rcon[j]是一个字，其值见下表。

常见魔改：

1.字节代换的时候使用逆s盒（逆的时候用s盒进行解密
2.对行位移进行魔改
3.对列混淆进行魔改
4.对中间轮数的加密顺序进行魔改

加解密代码

#include <stdint.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>

typedef struct{
    uint32_t eK[44], dK[44];    // encKey, decKey
    int Nr; // 10 rounds
}AesKey;

#define BLOCKSIZE 16  //AES-128分组长度为16字节

// uint8_t y[4] -> uint32_t x
#define LOAD32H(x, y) \
  do { (x) = ((uint32_t)((y)[0] & 0xff)<<24) | ((uint32_t)((y)[1] & 0xff)<<16) | \
             ((uint32_t)((y)[2] & 0xff)<<8)  | ((uint32_t)((y)[3] & 0xff));} while(0)

// uint32_t x -> uint8_t y[4]
#define STORE32H(x, y) \
  do { (y)[0] = (uint8_t)(((x)>>24) & 0xff); (y)[1] = (uint8_t)(((x)>>16) & 0xff);   \
       (y)[2] = (uint8_t)(((x)>>8) & 0xff); (y)[3] = (uint8_t)((x) & 0xff); } while(0)

// 从uint32_t x中提取从低位开始的第n个字节
#define BYTE(x, n) (((x) >> (8 * (n))) & 0xff)

/* used for keyExpansion */
// 字节替换然后循环左移1位
#define MIX(x) (((S[BYTE(x, 2)] << 24) & 0xff000000) ^ ((S[BYTE(x, 1)] << 16) & 0xff0000) ^ \
                ((S[BYTE(x, 0)] << 8) & 0xff00) ^ (S[BYTE(x, 3)] & 0xff))

// uint32_t x循环左移n位
#define ROF32(x, n)  (((x) << (n)) | ((x) >> (32-(n))))
// uint32_t x循环右移n位
#define ROR32(x, n)  (((x) >> (n)) | ((x) << (32-(n))))

/* for 128-bit blocks, Rijndael never uses more than 10 rcon values */
// AES-128轮常量
static const uint32_t rcon[10] = {
        0x01000000UL, 0x02000000UL, 0x04000000UL, 0x08000000UL, 0x10000000UL,
        0x20000000UL, 0x40000000UL, 0x80000000UL, 0x1B000000UL, 0x36000000UL
};
// S盒
unsigned char S[256] = {
        0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
        0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
        0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
        0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
        0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
        0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
        0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
        0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
        0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
        0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
        0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
        0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
        0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
        0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
        0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
        0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16
};

//逆S盒
unsigned char inv_S[256] = {
        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
};

/* copy in[16] to state[4][4] */
int loadStateArray(uint8_t (*state)[4], const uint8_t *in) {
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j) {
            state[j][i] = *in++;
        }
    }
    return 0;
}

/* copy state[4][4] to out[16] */
int storeStateArray(uint8_t (*state)[4], uint8_t *out) {
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j) {
            *out++ = state[j][i];
        }
    }
    return 0;
}

// 十六进制字符串转字节数组
int hex2bytes(const char *hex, uint8_t *bytes, int max_len) {
    int len = strlen(hex);
    if (len % 2 != 0 || len/2 > max_len) {
        return -1;
    }
    
    for (int i = 0; i < len; i += 2) {
        sscanf(hex + i, "%2hhx", &bytes[i/2]);
    }
    return len/2;
}

// 秘钥扩展 - 修复指针越界问题
int keyExpansion(const uint8_t *key, uint32_t keyLen, AesKey *aesKey) {

    if (NULL == key || NULL == aesKey){
        printf("keyExpansion param is NULL\n");
        return -1;
    }

    if (keyLen != 16){
        printf("keyExpansion keyLen = %d, Not support.\n", keyLen);
        return -1;
    }

    uint32_t *w = aesKey->eK;  //加密秘钥
    uint32_t *v = aesKey->dK;  //解密秘钥

    /* W[0-3] */
    for (int i = 0; i < 4; ++i) {
        LOAD32H(w[i], key + 4*i);
    }

    /* W[4-43] - 修复指针移动导致的越界问题 */
    for (int i = 4; i < 44; i += 4) {
        w[i] = w[i-4] ^ MIX(w[i-1]) ^ rcon[(i/4)-1];
        w[i+1] = w[i-3] ^ w[i];
        w[i+2] = w[i-2] ^ w[i+1];
        w[i+3] = w[i-1] ^ w[i+2];
    }

    // 解密秘钥矩阵为加密秘钥矩阵的倒序
    for (int j = 0; j < 11; ++j) {
        int ek_idx = 44 - 4 - 4*j;
        int dk_idx = 4*j;
        for (int i = 0; i < 4; ++i) {
            v[dk_idx + i] = w[ek_idx + i];
        }
    }

    return 0;
}

// 轮秘钥加
int addRoundKey(uint8_t (*state)[4], const uint32_t *key) {
    uint8_t k[4][4];

    /* i: row, j: col */
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j) {
            k[i][j] = (uint8_t) BYTE(key[j], 3 - i);  /* 把 uint32 key[4] 先转换为矩阵 uint8 k[4][4] */
            state[i][j] ^= k[i][j];
        }
    }

    return 0;
}

//字节替换
int subBytes(uint8_t (*state)[4]) {
    /* i: row, j: col */
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j) {
            state[i][j] = S[state[i][j]]; //直接使用原始字节作为S盒数据下标
        }
    }

    return 0;
}

//逆字节替换
int invSubBytes(uint8_t (*state)[4]) {
    /* i: row, j: col */
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j) {
            state[i][j] = inv_S[state[i][j]];
        }
    }
    return 0;
}

//行移位
int shiftRows(uint8_t (*state)[4]) {
    uint32_t block[4] = {0};

    /* i: row */
    for (int i = 0; i < 4; ++i) {
    //便于行循环移位，先把一行4字节拼成uint_32结构，移位后再转成独立的4个字节uint8_t
        LOAD32H(block[i], state[i]);
        block[i] = ROF32(block[i], 8*i);
        STORE32H(block[i], state[i]);
    }

    return 0;
}

//逆行移位
int invShiftRows(uint8_t (*state)[4]) {
    uint32_t block[4] = {0};

    /* i: row */
    for (int i = 0; i < 4; ++i) {
        LOAD32H(block[i], state[i]);
        block[i] = ROR32(block[i], 8*i);
        STORE32H(block[i], state[i]);
    }

    return 0;
}

/* Galois Field (256) Multiplication of two Bytes */
// 两字节的伽罗华域乘法运算
uint8_t GMul(uint8_t u, uint8_t v) {
    uint8_t p = 0;

    for (int i = 0; i < 8; ++i) {
        if (u & 0x01) {    //
            p ^= v;
        }

        int flag = (v & 0x80);
        v <<= 1;
        if (flag) {
            v ^= 0x1B; /* x^8 + x^4 + x^3 + x + 1 */
        }

        u >>= 1;
    }

    return p;
}

// 列混合
int mixColumns(uint8_t (*state)[4]) {
    uint8_t tmp[4][4];
    uint8_t M[4][4] = {{0x02, 0x03, 0x01, 0x01},
                       {0x01, 0x02, 0x03, 0x01},
                       {0x01, 0x01, 0x02, 0x03},
                       {0x03, 0x01, 0x01, 0x02}};

    /* copy state[4][4] to tmp[4][4] */
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j){
            tmp[i][j] = state[i][j];
        }
    }
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j) {  //伽罗华域加法和乘法
            state[i][j] = GMul(M[i][0], tmp[0][j]) ^ GMul(M[i][1], tmp[1][j])
                        ^ GMul(M[i][2], tmp[2][j]) ^ GMul(M[i][3], tmp[3][j]);
        }
    }
    return 0;
}

// 逆列混合
int invMixColumns(uint8_t (*state)[4]) {
    uint8_t tmp[4][4];
    uint8_t M[4][4] = {{0x0E, 0x0B, 0x0D, 0x09},
                       {0x09, 0x0E, 0x0B, 0x0D},
                       {0x0D, 0x09, 0x0E, 0x0B},
                       {0x0B, 0x0D, 0x09, 0x0E}};  //使用列混合矩阵的逆矩阵

    /* copy state[4][4] to tmp[4][4] */
    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j){
            tmp[i][j] = state[i][j];
        }
    }

    for (int i = 0; i < 4; ++i) {
        for (int j = 0; j < 4; ++j) {
            state[i][j] = GMul(M[i][0], tmp[0][j]) ^ GMul(M[i][1], tmp[1][j])
                          ^ GMul(M[i][2], tmp[2][j]) ^ GMul(M[i][3], tmp[3][j]);
        }
    }

    return 0;
}

// AES-128加密接口，输入key应为16字节长度，输入长度应该是16字节整倍数，
// 这样输出长度与输入长度相同，函数调用外部为输出数据分配内存
int aesEncrypt(const uint8_t *key, uint32_t keyLen, const uint8_t *pt, uint8_t *ct, uint32_t len) {

    AesKey aesKey;
    uint8_t *pos = ct;
    const uint32_t *rk = aesKey.eK;  //加密秘钥指针（修复注释错误）
    uint8_t out[BLOCKSIZE] = {0};
    uint8_t actualKey[16] = {0};
    uint8_t state[4][4] = {0};

    if (NULL == key || NULL == pt || NULL == ct){
        printf("param err.\n");
        return -1;
    }

    if (keyLen > 16){
        printf("keyLen must be 16.\n");
        return -1;
    }

    if (len % BLOCKSIZE){
        printf("inLen is invalid.\n");
        return -1;
    }

    memcpy(actualKey, key, keyLen);
    keyExpansion(actualKey, 16, &aesKey);  // 秘钥扩展

    // 使用ECB模式循环加密多个分组长度的数据
    for (int i = 0; i < len; i += BLOCKSIZE) {
        // 把16字节的明文转换为4x4状态矩阵来进行处理
        loadStateArray(state, pt);
        // 轮秘钥加
        addRoundKey(state, rk);

        for (int j = 1; j < 10; ++j) {
            rk += 4;
            subBytes(state);   // 字节替换
            shiftRows(state);  // 行移位
            mixColumns(state); // 列混合
            addRoundKey(state, rk); // 轮秘钥加
        }

        subBytes(state);    // 字节替换
        shiftRows(state);  // 行移位
        // 此处不进行列混合
        addRoundKey(state, rk+4); // 轮秘钥加
        
        // 把4x4状态矩阵转换为uint8_t一维数组输出保存
        storeStateArray(state, pos);

        pos += BLOCKSIZE;  // 加密数据内存指针移动到下一个分组
        pt += BLOCKSIZE;   // 明文数据指针移动到下一个分组
        rk = aesKey.eK;    // 恢复rk指针到秘钥初始位置
    }
    return 0;
}

// AES128解密， 参数要求同加密
int aesDecrypt(const uint8_t *key, uint32_t keyLen, const uint8_t *ct, uint8_t *pt, uint32_t len) {
    AesKey aesKey;
    uint8_t *pos = pt;
    const uint32_t *rk = aesKey.dK;  //解密秘钥指针
    uint8_t out[BLOCKSIZE] = {0};
    uint8_t actualKey[16] = {0};
    uint8_t state[4][4] = {0};

    if (NULL == key || NULL == ct || NULL == pt){
        printf("param err.\n");
        return -1;
    }

    if (keyLen > 16){
        printf("keyLen must be 16.\n");
        return -1;
    }

    if (len % BLOCKSIZE){
        printf("inLen is invalid.\n");
        return -1;
    }

    memcpy(actualKey, key, keyLen);
    keyExpansion(actualKey, 16, &aesKey);  //秘钥扩展，同加密

    for (int i = 0; i < len; i += BLOCKSIZE) {
        // 把16字节的密文转换为4x4状态矩阵来进行处理
        loadStateArray(state, ct);
        // 轮秘钥加，同加密
        addRoundKey(state, rk);

        for (int j = 1; j < 10; ++j) {
            rk += 4;
            invShiftRows(state);    // 逆行移位
            invSubBytes(state);     // 逆字节替换，这两步顺序可以颠倒
            addRoundKey(state, rk); // 轮秘钥加，同加密
            invMixColumns(state);   // 逆列混合
        }

        invSubBytes(state);   // 逆字节替换
        invShiftRows(state);  // 逆行移位
        // 此处没有逆列混合
        addRoundKey(state, rk+4);  // 轮秘钥加，同加密

        storeStateArray(state, pos);  // 保存明文数据
        pos += BLOCKSIZE;  // 输出数据内存指针移位分组长度
        ct += BLOCKSIZE;   // 输入数据内存指针移位分组长度
        rk = aesKey.dK;    // 恢复rk指针到秘钥初始位置
    }
    return 0;
}

int main(){
    // 16字节密钥
    char key[] = "FanBglFanBglOoO!";
    // 十六进制密文字符串
    char hex_ct[] = "d458af702a680ae4d089ce32fc39945d";
    // 存储转换后的字节密文
    uint8_t ct[BLOCKSIZE] = {0};
    // 存储解密后的明文
    uint8_t pt[BLOCKSIZE] = {0};
    
    // 转换十六进制字符串到字节数组
    int ct_len = hex2bytes(hex_ct, ct, BLOCKSIZE);
    if (ct_len != BLOCKSIZE) {
        printf("密文格式错误，长度应为32个十六进制字符\n");
        return -1;
    }
    
    // 解密：参数顺序为(key, key长度, 密文, 明文输出, 数据长度)
    int ret = aesDecrypt((uint8_t*)key, strlen(key), ct, pt, BLOCKSIZE);
    if (ret != 0) {
        printf("解密失败\n");
        return -1;
    }
    
    // 打印解密结果（十六进制格式）
    printf("解密结果(十六进制): ");
    for (int i = 0; i < BLOCKSIZE; i++) {
        printf("%02x", pt[i]);
    }
    printf("\n");
    
    // 打印解密结果（ASCII格式，若为可打印字符）
    printf("解密结果(ASCII): ");
    for (int i = 0; i < BLOCKSIZE; i++) {
        if (pt[i] >= 0x20 && pt[i] <= 0x7E) {
            printf("%c", pt[i]);
        } else {
            printf(".");
        }
    }
    printf("\n");
    
    return 0;
}