安卓漏洞学习（十六）：unicorn在逆向中的使用

unicorn是一个强大的工具，在没有调试环境的时候非常适合使用，但是开始模拟执行前要正确对内存，栈，寄存器进行初始化和赋值，还有灵活处理无法模拟执行的情况，这需要清晰得理解程序的汇编。

使用场景

Unicorn 适用于多种场景，包括但不限于：
动态分析: 在安全研究中，Unicorn 可以用于动态分析恶意软件，帮助研究人员理解其行为。
逆向工程: 开发者可以使用 Unicorn 模拟执行二进制文件，以便分析其逻辑和功能。
漏洞研究: Unicorn 可以帮助研究人员模拟漏洞利用过程，测试和验证漏洞的影响。
教育和培训: Unicorn 是学习计算机体系结构和操作系统的一个很好的工具，学生可以通过模拟器理解底层原理。

常用函数

模拟器初始化
unicorn.Uc(arch, mode)

内存映射
mem_map(address, size, perms=uc.UC_PROT_ALL)

向内存中写入数据 data为byte类型
mem_write(address, data)

向内存中读出数据
mem_read(address, size)

向寄存器中写入值
reg_write(reg_id, value)

向寄存器中读出值
reg_read(reg_id)

添加hook
hook_add(htype, callback, user_data=None, begin=1, end=0, arg1=0)

示例程序

#!/usr/bin/env python
# Sample code for ARM of Unicorn. Nguyen Anh Quynh <aquynh@gmail.com>
# Python sample ported by Loi Anh Tuan <loianhtuan@gmail.com>

from __future__ import print_function
from unicorn import *
from unicorn.arm_const import *


# code to be emulated
ARM_CODE   = b"\x37\x00\xa0\xe3\x03\x10\x42\xe0" # mov r0, #0x37; sub r1, r2, r3
THUMB_CODE = b"\x83\xb0" # sub    sp, #0xc
# memory address where emulation starts
ADDRESS    = 0x10000


# callback for tracing basic blocks
def hook_block(uc, address, size, user_data):
    print(">>> Tracing basic block at 0x%x, block size = 0x%x" %(address, size))


# callback for tracing instructions
def hook_code(uc, address, size, user_data):
    print(">>> Tracing instruction at 0x%x, instruction size = 0x%x" %(address, size))


# Test ARM
def test_arm():
    print("Emulate ARM code")
    try:
        # Initialize emulator in ARM mode
        mu = Uc(UC_ARCH_ARM, UC_MODE_ARM)

        # map 2MB memory for this emulation
        mu.mem_map(ADDRESS, 2 * 1024 * 1024)

        # write machine code to be emulated to memory
        mu.mem_write(ADDRESS, ARM_CODE)

        # initialize machine registers
        mu.reg_write(UC_ARM_REG_R0, 0x1234)
        mu.reg_write(UC_ARM_REG_R2, 0x6789)
        mu.reg_write(UC_ARM_REG_R3, 0x3333)
        mu.reg_write(UC_ARM_REG_APSR, 0xFFFFFFFF) #All application flags turned on
   
        # tracing all basic blocks with customized callback
        mu.hook_add(UC_HOOK_BLOCK, hook_block)

        # tracing one instruction at ADDRESS with customized callback
        mu.hook_add(UC_HOOK_CODE, hook_code, begin=ADDRESS, end=ADDRESS)

        # emulate machine code in infinite time
        mu.emu_start(ADDRESS, ADDRESS + len(ARM_CODE))

        # now print out some registers
        print(">>> Emulation done. Below is the CPU context")

        r0 = mu.reg_read(UC_ARM_REG_R0)
        r1 = mu.reg_read(UC_ARM_REG_R1)
        print(">>> R0 = 0x%x" %r0)
        print(">>> R1 = 0x%x" %r1)

    except UcError as e:
        print("ERROR: %s" % e)


def test_thumb():
    print("Emulate THUMB code")
    try:
        # Initialize emulator in thumb mode
        mu = Uc(UC_ARCH_ARM, UC_MODE_THUMB)

        # map 2MB memory for this emulation
        mu.mem_map(ADDRESS, 2 * 1024 * 1024)

        # write machine code to be emulated to memory
        mu.mem_write(ADDRESS, THUMB_CODE)

        # initialize machine registers
        mu.reg_write(UC_ARM_REG_SP, 0x1234)

        # tracing all basic blocks with customized callback
        mu.hook_add(UC_HOOK_BLOCK, hook_block)

        # tracing all instructions with customized callback
        mu.hook_add(UC_HOOK_CODE, hook_code)

        # emulate machine code in infinite time
        # Note we start at ADDRESS | 1 to indicate THUMB mode.
        mu.emu_start(ADDRESS | 1, ADDRESS + len(THUMB_CODE))

        # now print out some registers
        print(">>> Emulation done. Below is the CPU context")

        sp = mu.reg_read(UC_ARM_REG_SP)
        print(">>> SP = 0x%x" %sp)

    except UcError as e:
        print("ERROR: %s" % e)


if __name__ == '__main__':
    test_arm()
    print("=" * 26)
    test_thumb()