【免杀】PE文件分析

最近代码能力飞速提升，顺便复习一下

一般就是

• DOS头：IMAGE_DOS_HEADER结构体
• PE头：IMAGE_NT_HEADERS结构体
• Section头：IMAGE_SECTION_HEADER结构体

OK，如果要分析PE文件的话，首先把文件读取出来

那么如何解析呢？这就是C/C++非常方便的一点：直接使用结构体转换，例如把地址值解析为数值
总体就是解释内存中的值

DOS 头

先看DOSHeader吧

typedef struct _IMAGE_DOS_HEADER {      // DOS .EXE header
    WORD   e_magic;                     // Magic number
    WORD   e_cblp;                      // Bytes on last page of file
    WORD   e_cp;                        // Pages in file
    WORD   e_crlc;                      // Relocations
    WORD   e_cparhdr;                   // Size of header in paragraphs
    WORD   e_minalloc;                  // Minimum extra paragraphs needed
    WORD   e_maxalloc;                  // Maximum extra paragraphs needed
    WORD   e_ss;                        // Initial (relative) SS value
    WORD   e_sp;                        // Initial SP value
    WORD   e_csum;                      // Checksum
    WORD   e_ip;                        // Initial IP value
    WORD   e_cs;                        // Initial (relative) CS value
    WORD   e_lfarlc;                    // File address of relocation table
    WORD   e_ovno;                      // Overlay number
    WORD   e_res[4];                    // Reserved words
    WORD   e_oemid;                     // OEM identifier (for e_oeminfo)
    WORD   e_oeminfo;                   // OEM information; e_oemid specific
    WORD   e_res2[10];                  // Reserved words
    LONG   e_lfanew;                    // File address of new exe header
  } IMAGE_DOS_HEADER, *PIMAGE_DOS_HEADER;

需要的是e_lfanew

NT头

文件起始地址+e_lfanew = NT头位置

得到NT头位置后

typedef struct _IMAGE_NT_HEADERS64 {
    DWORD Signature;
    IMAGE_FILE_HEADER FileHeader;
    IMAGE_OPTIONAL_HEADER64 OptionalHeader;
} IMAGE_NT_HEADERS64, *PIMAGE_NT_HEADERS64;

重要的是IMAGE_OPTIONAL_HEADER，其实都一样，可以从FileHeader得到32位还是64位，

typedef struct _IMAGE_FILE_HEADER {
    WORD    Machine;
    WORD    NumberOfSections;
    DWORD   TimeDateStamp;
    DWORD   PointerToSymbolTable;
    DWORD   NumberOfSymbols;
    WORD    SizeOfOptionalHeader;
    WORD    Characteristics;
} IMAGE_FILE_HEADER, *PIMAGE_FILE_HEADER;

• 0x8664：adm64位
• 0x014C：intel32位

接下来以64位举例子

typedef struct _IMAGE_OPTIONAL_HEADER64 {
    WORD        Magic;
    BYTE        MajorLinkerVersion;
    BYTE        MinorLinkerVersion;
    DWORD       SizeOfCode;
    DWORD       SizeOfInitializedData;
    DWORD       SizeOfUninitializedData;
    DWORD       AddressOfEntryPoint;
    DWORD       BaseOfCode;
    ULONGLONG   ImageBase;
    DWORD       SectionAlignment;
    DWORD       FileAlignment;
    WORD        MajorOperatingSystemVersion;
    WORD        MinorOperatingSystemVersion;
    WORD        MajorImageVersion;
    WORD        MinorImageVersion;
    WORD        MajorSubsystemVersion;
    WORD        MinorSubsystemVersion;
    DWORD       Win32VersionValue;
    DWORD       SizeOfImage;
    DWORD       SizeOfHeaders;
    DWORD       CheckSum;
    WORD        Subsystem;
    WORD        DllCharacteristics;
    ULONGLONG   SizeOfStackReserve;
    ULONGLONG   SizeOfStackCommit;
    ULONGLONG   SizeOfHeapReserve;
    ULONGLONG   SizeOfHeapCommit;
    DWORD       LoaderFlags;
    DWORD       NumberOfRvaAndSizes;
    IMAGE_DATA_DIRECTORY DataDirectory[IMAGE_NUMBEROF_DIRECTORY_ENTRIES];
} IMAGE_OPTIONAL_HEADER64, *PIMAGE_OPTIONAL_HEADER64;

到这里我写了部分代码，结合IDA就很好理解了

如果还要继续看的话就是DataDirectory

typedef struct _IMAGE_DATA_DIRECTORY {
    DWORD   VirtualAddress;
    DWORD   Size;
} IMAGE_DATA_DIRECTORY, *PIMAGE_DATA_DIRECTORY;

打印虚拟地址

其实就是导入导出表之类的东西

Nt->ImageBase+这里的偏移，就是运行时的位置

// Directory Entries

#define IMAGE_DIRECTORY_ENTRY_EXPORT          0   // Export Directory
#define IMAGE_DIRECTORY_ENTRY_IMPORT          1   // Import Directory
#define IMAGE_DIRECTORY_ENTRY_RESOURCE        2   // Resource Directory
#define IMAGE_DIRECTORY_ENTRY_EXCEPTION       3   // Exception Directory
#define IMAGE_DIRECTORY_ENTRY_SECURITY        4   // Security Directory
#define IMAGE_DIRECTORY_ENTRY_BASERELOC       5   // Base Relocation Table
#define IMAGE_DIRECTORY_ENTRY_DEBUG           6   // Debug Directory
//      IMAGE_DIRECTORY_ENTRY_COPYRIGHT       7   // (X86 usage)
#define IMAGE_DIRECTORY_ENTRY_ARCHITECTURE    7   // Architecture Specific Data
#define IMAGE_DIRECTORY_ENTRY_GLOBALPTR       8   // RVA of GP
#define IMAGE_DIRECTORY_ENTRY_TLS             9   // TLS Directory
#define IMAGE_DIRECTORY_ENTRY_LOAD_CONFIG    10   // Load Configuration Directory
#define IMAGE_DIRECTORY_ENTRY_BOUND_IMPORT   11   // Bound Import Directory in headers
#define IMAGE_DIRECTORY_ENTRY_IAT            12   // Import Address Table
#define IMAGE_DIRECTORY_ENTRY_DELAY_IMPORT   13   // Delay Load Import Descriptors
#define IMAGE_DIRECTORY_ENTRY_COM_DESCRIPTOR 14   // COM Runtime descriptor

节表相关

再回到NT头中的FileHeader，提取得到节数量

DOS头和NT头的大小加起来后面就是第一个Section

typedef struct _IMAGE_SECTION_HEADER {
    BYTE    Name[IMAGE_SIZEOF_SHORT_NAME];
    union {
            DWORD   PhysicalAddress;
            DWORD   VirtualSize;
    } Misc;
    DWORD   VirtualAddress;
    DWORD   SizeOfRawData;
    DWORD   PointerToRawData;
    DWORD   PointerToRelocations;
    DWORD   PointerToLinenumbers;
    WORD    NumberOfRelocations;
    WORD    NumberOfLinenumbers;
    DWORD   Characteristics;
} IMAGE_SECTION_HEADER, *PIMAGE_SECTION_HEADER;

BOOL FilePE::bGetSectionList() {
	if (this->FileContent.length() == 0) {
		Error("File content is zero", DEBUG);
		return FALSE;
	}
	if (this->pHeaderNT == NULL) {
		Error("NT head not initialize", DEBUG);
		return FALSE;
	}
	DWORD SectionNum = this->pHeaderNT->FileHeader.NumberOfSections;
	this->SecNum = SectionNum;
	this->SectionList = (PIMAGE_SECTION_HEADER*)malloc((SectionNum + 1) * sizeof(PIMAGE_SECTION_HEADER));
	if (this->SectionList == NULL) {
		Error("Allcate section list memory failed\n", DEBUG);
		return FALSE;
	}
	for (size_t i = 0; i < SectionNum; i++)
	{
		SectionList[i] = PIMAGE_SECTION_HEADER(
			&this->FileContent[0] + this->pHeaderDOS->e_lfanew 
			+ sizeof(IMAGE_NT_HEADERS) + i * sizeof(IMAGE_SECTION_HEADER));
	}
	return TRUE;
}

IAT表

I. 如何找到文件的IAT表

IAT叫Import Address Table，当我们的程序需要外部库的函数时，就会从这里开始调用

IAT表的地址并不在任何头中，不过我们之前分析Directory的时候就发现会有一个IMAGE_DIRECTORY_ENTRY_IAT，但它不是导入表，真正的IAT描述：

pHeaderNT->OptionalHeader.DataDirectory[IMAGE_DIRECTORY_ENTRY_IMPORT]

按道理来说VirtualAddress+ImageBase就是运行起来的地址，这里我没有加上

突然想起来我们在分析节表的时候也存在类似的 基地址+偏移

对于这个结构体之前的只能用这块儿的目录

对应文件中地址为28fc-2000+1400 = 1cfc

有点意思，查阅资料发现对应的结构体：_IMAGE_IMPORT_DESCRIPTOR，MSDN中并没有对应说明

typedef struct _IMAGE_IMPORT_DESCRIPTOR {
    union {
        DWORD   Characteristics;            // 0 for terminating null import descriptor
        DWORD   OriginalFirstThunk;         // RVA to original unbound IAT (PIMAGE_THUNK_DATA)
    } DUMMYUNIONNAME;
    DWORD   TimeDateStamp; 
    DWORD   ForwarderChain;                 // -1 if no forwarders
    DWORD   Name;
    DWORD   FirstThunk;                     // RVA to IAT (if bound this IAT has actual addresses)
} IMAGE_IMPORT_DESCRIPTOR;
typedef IMAGE_IMPORT_DESCRIPTOR UNALIGNED *PIMAGE_IMPORT_DESCRIPTOR;

有个问题就是这块地址是运行时写入IAT相关信息，我们的静态分析到这一步就算断了

这里我设计了一个BOOL bGetIAT();函数，直接去读程序的内存，为了简单，就先关闭ASLR

已经成功读取一个信息，接下来办法全部找出来，自然想到的就是Name为0就退出，但是由于总数不知道，所以需要一个动态容器，我用的vector

vector<PIMAGE_IMPORT_DESCRIPTOR> pIATList;

按照一样的方法全部得到后，再次尝试在运行中读取

但是很多PE分析工具静态也能看得到，利用的是RVA->RAW的转换

2d52-2000+1400=2152

void FilePE::PrintIATStatic() {
	if (this->pIATList.size() == 0) {
		Error("IAT List empty", DEBUG);
		return;
	}
	DWORD VA = 0;
	for (size_t i = 0; i < this->pIATList.size(); i++)
	{
		VA = this->dwVAToRaw(this->pIATList[i]->Name);
		cout << "DLL : " << &this->FileContent[0] + VA << endl;
	}
}

II. 找到导入函数

通过OriginalFirstThunk，基本就是OriginalFirstThunk进行转化找到RAW，RAW地方的地址再转为RAW就找到了，最终的位置是一个_IMAGE_IMPORT_BY_NAME结构体

typedef struct _IMAGE_IMPORT_BY_NAME {
    WORD    Hint;
    CHAR   Name[1];
} IMAGE_IMPORT_BY_NAME, *PIMAGE_IMPORT_BY_NAME;

void FilePE::PrintFunction(PIMAGE_IMPORT_DESCRIPTOR pIAT) {
	DWORD64 VA = *PDWORD64(&this->FileContent[0] + this->dwVAToRaw(pIAT->OriginalFirstThunk));
	for (size_t i = 1; VA != 0; i++)
	{
		PIMAGE_IMPORT_BY_NAME IatName = PIMAGE_IMPORT_BY_NAME(&this->FileContent[0] + this->dwVAToRaw(VA));
		cout << "    Function " << IatName->Name << endl;
		VA = *PDWORD64(&this->FileContent[0] + this->dwVAToRaw(pIAT->OriginalFirstThunk) + i * sizeof(DWORD64));
	}
}

找到入口函数

很简单，在上面的nt->option_header.AddressOfEntryPoint里面，可以直接ImageBase+AddressOfEntryPoint，二进制数据都对的上