From 639fb264454180de31119f0401993406e282a409 Mon Sep 17 00:00:00 2001 From: Kekoa Kaaikala Date: Tue, 16 Aug 2022 19:27:56 +0000 Subject: [PATCH] Agent: Improve the speed of bit flipping code - Remove a function call - Use a generator - Use a more efficient flip calculation (subtraction instead of xor) Issue #2123 --- CHANGELOG.md | 1 + .../utils/bit_manipulators.py | 47 ++++++++----------- .../utils/test_bit_manipulators.py | 27 +++++++++-- 3 files changed, 44 insertions(+), 31 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 0e7a7a0d7..4ad014869 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -55,6 +55,7 @@ Changelog](https://keepachangelog.com/en/1.0.0/). - `/api/auth` endpoint to `/api/authenticate`. #2105 - `/api/registration` endpoint to `/api/register`. #2105 - `/api/file-upload` endpoit to `/api/pba/upload`. #2154 +- Improved the speed of ransomware encryption by 2-3x. #2123 ### Removed - VSFTPD exploiter. #1533 diff --git a/monkey/infection_monkey/utils/bit_manipulators.py b/monkey/infection_monkey/utils/bit_manipulators.py index 8de1460ed..ae04d8ff7 100644 --- a/monkey/infection_monkey/utils/bit_manipulators.py +++ b/monkey/infection_monkey/utils/bit_manipulators.py @@ -1,30 +1,21 @@ +from typing import Iterable + + +def generate_flipped_bits(data: bytes) -> Iterable[int]: + """ + Yield bytes with the bits flipped + + :param data: The data whose bits to flip + """ + for byte in data: + yield 255 - byte + + def flip_bits(data: bytes) -> bytes: - flipped_bits = bytearray(len(data)) + """ + Flip all bits in the given bytes - for i, byte in enumerate(data): - # TODO: The function call to flip_bits_in_single_byte() adds significant - # overhead. While python is supposed to "inline" function calls - # like this, I've yet to see any changes in runtime that indicate - # this optimization is actually happening. - # - # The value of breaking this into separate functions is the unit - # test that tests all possible bytes (0-255). This gives us - # confidence that our bit-flip operation is correct. - # - # Remove the flip_bits_in_single_byte() function and rework the - # unit tests so that we still have a high-degree of confidence - # that this code is correct. - # - # EDIT: I believe PyPy will attempt to inline functions - # automatically. I don't know that CPython makes any such - # optimizations. - flipped_bits[i] = flip_bits_in_single_byte(byte) - - return bytes(flipped_bits) - - -def flip_bits_in_single_byte(byte) -> int: - # TODO: The operation `255 - byte` appears to be 12% faster than 255 ^ byte. - # Switch the operator and thoroughly test the ransomware payload to - # ensure this doesn't introduce any defects. - return 255 ^ byte + :param data: The bytes whose bits to flip + :return: Bytes with the bits flipped + """ + return bytes(generate_flipped_bits(data)) diff --git a/monkey/tests/unit_tests/infection_monkey/utils/test_bit_manipulators.py b/monkey/tests/unit_tests/infection_monkey/utils/test_bit_manipulators.py index 0b866f634..fdfb2a61f 100644 --- a/monkey/tests/unit_tests/infection_monkey/utils/test_bit_manipulators.py +++ b/monkey/tests/unit_tests/infection_monkey/utils/test_bit_manipulators.py @@ -1,9 +1,30 @@ from infection_monkey.utils import bit_manipulators +from infection_monkey.utils.bit_manipulators import flip_bits -def test_flip_bits_in_single_byte(): - for i in range(0, 256): - assert bit_manipulators.flip_bits_in_single_byte(i) == (255 - i) +def test_flip_all_bits(): + input_bytes = bytes( + b"\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" + b"\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" + b"\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f" + b"\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f" + b"\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f" + b"\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f" + b"\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f" + b"\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f" + b"\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" + b"\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" + b"\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf" + b"\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" + b"\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" + b"\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" + b"\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + b"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff" + ) + + expected_bytes = bytes(reversed(input_bytes)) + + assert flip_bits(input_bytes) == expected_bytes def test_flip_bits():