我想加密大型文件或数据流

对于大多数文件加密用例,我们建议使用AES128_GCM_HKDF_1MB 密钥类型的流式 AEAD 基元。

流式 AEAD(带关联数据的认证加密)基元非常适用于加密无法存储在内存中的实时数据流或大型文件。与 AEAD 类似,它也是对称的,使用单个密钥进行加密和解密。

以下示例可帮助您开始使用 Streaming AEAD 基元:

Go

import (
	"bytes"
	"fmt"
	"io"
	"log"
	"os"
	"path/filepath"

	"github.com/tink-crypto/tink-go/v2/insecurecleartextkeyset"
	"github.com/tink-crypto/tink-go/v2/keyset"
	"github.com/tink-crypto/tink-go/v2/streamingaead"
)

func Example() {
	// A keyset created with "tinkey create-keyset --key-template=AES256_CTR_HMAC_SHA256_1MB". Note
	// that this keyset has the secret key information in cleartext.
	jsonKeyset := `{
    "primaryKeyId": 1720777699,
    "key": [{
        "keyData": {
            "typeUrl": "type.googleapis.com/google.crypto.tink.AesCtrHmacStreamingKey",
            "keyMaterialType": "SYMMETRIC",
            "value": "Eg0IgCAQIBgDIgQIAxAgGiDtesd/4gCnQdTrh+AXodwpm2b6BFJkp043n+8mqx0YGw=="
        },
        "outputPrefixType": "RAW",
        "keyId": 1720777699,
        "status": "ENABLED"
    }]
	}`

	// Create a keyset handle from the cleartext keyset in the previous
	// step. The keyset handle provides abstract access to the underlying keyset to
	// limit the exposure of accessing the raw key material. WARNING: In practice,
	// it is unlikely you will want to use an insecurecleartextkeyset, as it implies
	// that your key material is passed in cleartext, which is a security risk.
	// Consider encrypting it with a remote key in Cloud KMS, AWS KMS or HashiCorp Vault.
	// See https://github.com/google/tink/blob/master/docs/GOLANG-HOWTO.md#storing-and-loading-existing-keysets.
	keysetHandle, err := insecurecleartextkeyset.Read(
		keyset.NewJSONReader(bytes.NewBufferString(jsonKeyset)))
	if err != nil {
		log.Fatal(err)
	}

	// Retrieve the StreamingAEAD primitive we want to use from the keyset handle.
	primitive, err := streamingaead.New(keysetHandle)
	if err != nil {
		log.Fatal(err)
	}

	// Create a file with the plaintext.
	dir, err := os.MkdirTemp("", "streamingaead")
	if err != nil {
		log.Fatal(err)
	}
	defer os.RemoveAll(dir)
	plaintextPath := filepath.Join(dir, "plaintext")
	if err := os.WriteFile(plaintextPath, []byte("this data needs to be encrypted"), 0666); err != nil {
		log.Fatal(err)
	}
	plaintextFile, err := os.Open(plaintextPath)
	if err != nil {
		log.Fatal(err)
	}

	// associatedData defines the context of the encryption. Here, we include the path of the
	// plaintext file.
	associatedData := []byte("associatedData for " + plaintextPath)

	// Encrypt the plaintext file and write the output to the ciphertext file. In this case the
	// primary key of the keyset will be used (which is also the only key in this example).
	ciphertextPath := filepath.Join(dir, "ciphertext")
	ciphertextFile, err := os.Create(ciphertextPath)
	if err != nil {
		log.Fatal(err)
	}
	w, err := primitive.NewEncryptingWriter(ciphertextFile, associatedData)
	if err != nil {
		log.Fatal(err)
	}
	if _, err := io.Copy(w, plaintextFile); err != nil {
		log.Fatal(err)
	}
	if err := w.Close(); err != nil {
		log.Fatal(err)
	}
	if err := ciphertextFile.Close(); err != nil {
		log.Fatal(err)
	}
	if err := plaintextFile.Close(); err != nil {
		log.Fatal(err)
	}

	// Decrypt the ciphertext file and write the output to the decrypted file. The
	// decryption finds the correct key in the keyset and decrypts the ciphertext.
	// If no key is found or decryption fails, it returns an error.
	ciphertextFile, err = os.Open(ciphertextPath)
	if err != nil {
		log.Fatal(err)
	}
	decryptedPath := filepath.Join(dir, "decrypted")
	decryptedFile, err := os.Create(decryptedPath)
	if err != nil {
		log.Fatal(err)
	}
	r, err := primitive.NewDecryptingReader(ciphertextFile, associatedData)
	if err != nil {
		log.Fatal(err)
	}
	if _, err := io.Copy(decryptedFile, r); err != nil {
		log.Fatal(err)
	}
	if err := decryptedFile.Close(); err != nil {
		log.Fatal(err)
	}
	if err := ciphertextFile.Close(); err != nil {
		log.Fatal(err)
	}

	// Print the content of the decrypted file.
	b, err := os.ReadFile(decryptedPath)
	if err != nil {
		log.Fatal(err)
	}
	fmt.Println(string(b))
	// Output: this data needs to be encrypted
}

Java

package streamingaead;

import static java.nio.charset.StandardCharsets.UTF_8;

import com.google.crypto.tink.InsecureSecretKeyAccess;
import com.google.crypto.tink.KeysetHandle;
import com.google.crypto.tink.RegistryConfiguration;
import com.google.crypto.tink.StreamingAead;
import com.google.crypto.tink.TinkJsonProtoKeysetFormat;
import com.google.crypto.tink.streamingaead.StreamingAeadConfig;
import java.io.IOException;
import java.nio.ByteBuffer;
import java.nio.channels.FileChannel;
import java.nio.channels.ReadableByteChannel;
import java.nio.channels.WritableByteChannel;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.StandardOpenOption;
import java.security.GeneralSecurityException;

/**
 * A command-line utility for encrypting files with Streaming AEAD.
 *
 * <p>It loads cleartext keys from disk - this is not recommended!
 *
 * <p>It requires the following arguments:
 *
 * <ul>
 *   <li>mode: Can be "encrypt" or "decrypt" to encrypt/decrypt the input to the output.
 *   <li>key-file: Read the key material from this file.
 *   <li>input-file: Read the input from this file.
 *   <li>output-file: Write the result to this file.
 *   <li>[optional] associated-data: Associated data used for the encryption or decryption.
 */
public final class StreamingAeadExample {
  private static final String MODE_ENCRYPT = "encrypt";
  private static final String MODE_DECRYPT = "decrypt";
  private static final int BLOCK_SIZE_IN_BYTES = 8 * 1024;

  public static void main(String[] args) throws Exception {
    if (args.length != 4 && args.length != 5) {
      System.err.printf("Expected 4 or 5 parameters, got %d\n", args.length);
      System.err.println(
          "Usage: java StreamingAeadExample encrypt/decrypt key-file input-file output-file"
              + " [associated-data]");
      System.exit(1);
    }
    String mode = args[0];
    Path keyFile = Paths.get(args[1]);
    Path inputFile = Paths.get(args[2]);
    Path outputFile = Paths.get(args[3]);
    byte[] associatedData = new byte[0];
    if (args.length == 5) {
      associatedData = args[4].getBytes(UTF_8);
    }

    // Initialize Tink: register all Streaming AEAD key types with the Tink runtime
    StreamingAeadConfig.register();

    // Read the keyset into a KeysetHandle
    KeysetHandle handle =
        TinkJsonProtoKeysetFormat.parseKeyset(
            new String(Files.readAllBytes(keyFile), UTF_8), InsecureSecretKeyAccess.get());

    // Get the primitive
    StreamingAead streamingAead =
        handle.getPrimitive(RegistryConfiguration.get(), StreamingAead.class);

    // Use the primitive to encrypt/decrypt files
    if (mode.equals(MODE_ENCRYPT)) {
      encryptFile(streamingAead, inputFile, outputFile, associatedData);
    } else if (mode.equals(MODE_DECRYPT)) {
      decryptFile(streamingAead, inputFile, outputFile, associatedData);
    } else {
      System.err.println(
          "The first argument must be either "
              + MODE_ENCRYPT
              + " or "
              + MODE_DECRYPT
              + ", got: "
              + mode);
      System.exit(1);
    }
  }

  private static void encryptFile(
      StreamingAead streamingAead, Path inputFile, Path outputFile, byte[] associatedData)
      throws GeneralSecurityException, IOException {
    try (WritableByteChannel encryptingChannel =
            streamingAead.newEncryptingChannel(
                FileChannel.open(outputFile, StandardOpenOption.WRITE, StandardOpenOption.CREATE),
                associatedData);
        FileChannel inputChannel = FileChannel.open(inputFile, StandardOpenOption.READ)) {
      ByteBuffer byteBuffer = ByteBuffer.allocate(BLOCK_SIZE_IN_BYTES);
      while (true) {
        int read = inputChannel.read(byteBuffer);
        if (read <= 0) {
          return;
        }
        byteBuffer.flip();
        while (byteBuffer.hasRemaining()) {
          encryptingChannel.write(byteBuffer);
        }
        byteBuffer.clear();
      }
    }
  }

  private static void decryptFile(
      StreamingAead streamingAead, Path inputFile, Path outputFile, byte[] associatedData)
      throws GeneralSecurityException, IOException {
    try (ReadableByteChannel decryptingChannel =
            streamingAead.newDecryptingChannel(
                FileChannel.open(inputFile, StandardOpenOption.READ), associatedData);
        FileChannel outputChannel =
            FileChannel.open(outputFile, StandardOpenOption.WRITE, StandardOpenOption.CREATE)) {
      ByteBuffer byteBuffer = ByteBuffer.allocate(BLOCK_SIZE_IN_BYTES);
      while (true) {
        int read = decryptingChannel.read(byteBuffer);
        if (read <= 0) {
          return;
        }
        byteBuffer.flip();
        while (byteBuffer.hasRemaining()) {
          outputChannel.write(byteBuffer);
        }
        byteBuffer.clear();
      }
    }
  }

  private StreamingAeadExample() {}
}

Python

"""A command-line utility for using streaming AEAD for a file.

It loads cleartext keys from disk - this is not recommended!

It requires 4 arguments (and one optional one):
  mode: either 'encrypt' or 'decrypt'
  keyset_path: name of the file with the keyset to be used for encryption or
    decryption
  input_path: name of the file with the input data to be encrypted or decrypted
  output_path: name of the file to write the ciphertext respectively plaintext
    to
  [optional] associated_data: the associated data used for encryption/decryption
    provided as a string.
"""

from typing import BinaryIO

from absl import app
from absl import flags
from absl import logging
import tink
from tink import secret_key_access
from tink import streaming_aead

FLAGS = flags.FLAGS
BLOCK_SIZE = 1024 * 1024  # The CLI tool will read/write at most 1 MB at once.

flags.DEFINE_enum('mode', None, ['encrypt', 'decrypt'],
                  'Selects if the file should be encrypted or decrypted.')
flags.DEFINE_string('keyset_path', None,
                    'Path to the keyset used for encryption or decryption.')
flags.DEFINE_string('input_path', None, 'Path to the input file.')
flags.DEFINE_string('output_path', None, 'Path to the output file.')
flags.DEFINE_string('associated_data', None,
                    'Associated data used for the encryption or decryption.')


def read_as_blocks(file: BinaryIO):
  """Generator function to read from a file BLOCK_SIZE bytes.

  Args:
    file: The file object to read from.

  Yields:
    Returns up to BLOCK_SIZE bytes from the file.
  """
  while True:
    data = file.read(BLOCK_SIZE)
    # If file was opened in rawIO, EOF is only reached when b'' is returned.
    # pylint: disable=g-explicit-bool-comparison
    if data == b'':
      break
    # pylint: enable=g-explicit-bool-comparison
    yield data


def encrypt_file(input_file: BinaryIO, output_file: BinaryIO,
                 associated_data: bytes,
                 primitive: streaming_aead.StreamingAead):
  """Encrypts a file with the given streaming AEAD primitive.

  Args:
    input_file: File to read from.
    output_file: File to write to.
    associated_data: Associated data provided for the AEAD.
    primitive: The streaming AEAD primitive used for encryption.
  """
  with primitive.new_encrypting_stream(output_file,
                                       associated_data) as enc_stream:
    for data_block in read_as_blocks(input_file):
      enc_stream.write(data_block)


def decrypt_file(input_file: BinaryIO, output_file: BinaryIO,
                 associated_data: bytes,
                 primitive: streaming_aead.StreamingAead):
  """Decrypts a file with the given streaming AEAD primitive.

  This function will cause the program to exit with 1 if the decryption fails.

  Args:
    input_file: File to read from.
    output_file: File to write to.
    associated_data: Associated data provided for the AEAD.
    primitive: The streaming AEAD primitive used for decryption.
  """
  try:
    with primitive.new_decrypting_stream(input_file,
                                         associated_data) as dec_stream:
      for data_block in read_as_blocks(dec_stream):
        output_file.write(data_block)
  except tink.TinkError as e:
    logging.exception('Error decrypting ciphertext: %s', e)
    exit(1)


def main(argv):
  del argv

  associated_data = b'' if not FLAGS.associated_data else bytes(
      FLAGS.associated_data, 'utf-8')

  # Initialise Tink.
  try:
    streaming_aead.register()
  except tink.TinkError as e:
    logging.exception('Error initialising Tink: %s', e)
    return 1

  # Read the keyset into a keyset_handle.
  with open(FLAGS.keyset_path, 'rt') as keyset_file:
    try:
      text = keyset_file.read()
      keyset_handle = tink.json_proto_keyset_format.parse(
          text, secret_key_access.TOKEN
      )
    except tink.TinkError as e:
      logging.exception('Error reading key: %s', e)
      return 1

  # Get the primitive.
  try:
    streaming_aead_primitive = keyset_handle.primitive(
        streaming_aead.StreamingAead)
  except tink.TinkError as e:
    logging.exception('Error creating streaming AEAD primitive from keyset: %s',
                      e)
    return 1

  # Encrypt or decrypt the file.
  with open(FLAGS.input_path, 'rb') as input_file:
    with open(FLAGS.output_path, 'wb') as output_file:
      if FLAGS.mode == 'encrypt':
        encrypt_file(input_file, output_file, associated_data,
                     streaming_aead_primitive)
      elif FLAGS.mode == 'decrypt':
        decrypt_file(input_file, output_file, associated_data,
                     streaming_aead_primitive)


if __name__ == '__main__':
  flags.mark_flag_as_required('mode')
  flags.mark_flag_as_required('keyset_path')
  flags.mark_flag_as_required('input_path')
  flags.mark_flag_as_required('output_path')
  app.run(main)

流式 AEAD

流式 AEAD 基元可为流式数据提供认证加密。如果要加密的数据过大,无法在单个步骤中处理,此功能非常有用。典型用例包括加密大型文件或实时数据流。

加密是按分段进行的,这些分段绑定到其在密文中的位置,无法移除或重新排序。一个密文中的分段无法插入另一个密文中。如需修改现有密文,必须重新加密整个数据流。1

解密速度很快,因为一次只解密和身份验证密文的一部分。无需处理整个密文即可获取部分明文。

流式 AEAD 实现符合 AEAD 定义,并且具有 nOAE 安全性。它们具有以下属性:

  • Secrecy:除了长度之外,关于明文的所有信息均不为人知。
  • Authenticity:无法在不被检测的情况下更改密文底层的加密明文。
  • Symmetric:使用相同的密钥加密明文和解密密文。
  • 随机化:加密是随机的。具有相同明文的两条消息会产生不同的密文。攻击者无法知道哪个密文与给定明文相对应。

相关数据

流式 AEAD 基元可用于将密文与特定关联数据相关联。假设您有一个包含字段 user-idencrypted-medical-history 的数据库:在这种情况下,在加密 encrypted-medical-history 时,user-id 可以用作关联数据。这样可防止攻击者将一个用户的医疗记录从转移到另一个用户。

选择密钥类型

对于大多数用途,我们建议使用 AES128_GCM_HKDF_1MB。一般来说:

  • AES-GCM-HKDF
    • AES128_GCM_HKDF_1MB(或 AES256_GCM_HKDF_1MB)速度更快。它可以加密 264 个文件,每个文件最多包含 264 个字节。加密和解密过程中会消耗大约 1 MB 的内存。
    • AES128_GCM_HKDF_4KB 会消耗大约 4 KB 的内存,如果系统内存不多,则是一个不错的选择。
  • AES-CTR HMAC
    • AES128_CTR_HMAC_SHA256_1MB(或 AES256_CTR_HMAC_SHA256_1MB)是一种更为保守的选项。

安全保证

流式 AEAD 实现提供以下功能:

  • CCA2 安全性。
  • 身份验证强度至少为 80 位。
  • 能够加密至少 264 个消息3,总计 251 字节2。任何攻击都无法使用最多 232 个已选明文或已选密文,成功概率大于 2-32

  1. 存在此限制的原因是使用了 AES-GCM 加密算法。在同一位置加密不同的明文段相当于重复使用 IV,这违反了 AES-GCM 的安全保证。另一个原因是,这样可以防止回滚攻击,攻击者可能会尝试在不被检测的情况下恢复文件的旧版本。 

  2. 支持 232 个分段,每个分段包含 segment_size - tag_size 字节的明文。对于 1 MB 的段,明文总大小为 232 * (220-16) ≈ 251 字节。 

  3. 如果重复使用派生密钥 (128 位) 和 Nonce 前缀(独立的随机 7 字节值)组合,流式 AEAD 将变得不安全。我们采用了 184 位碰撞抵抗性,如果我们希望成功概率小于 2-32,则大致相当于 264 个消息。