\documentclass[a4paper,titlepage,12pt]{article}
 \usepackage{amssymb}
 \usepackage{pslatex}
 \usepackage[dvips]{graphicx}
 \usepackage{wrapfig}
 \usepackage{url}
 \date{}
 
 \begin{document}
 
     \begin{center}
 	\huge Creating signatures for ClamAV\\
 	\vspace{2cm}
     \end{center}
 
     \noindent
     \section{Introduction}
     CVD (ClamAV Virus Database) is a digitally signed tarball file that
     contains one or more databases. The header is a 512 bytes long string
     with colon separated fields:
     \begin{verbatim}
 ClamAV-VDB:build time:version:number of signatures:functionality
 level required:MD5 checksum:digital signature:builder name:build time (sec)
     \end{verbatim}
     \verb+sigtool --info+ displays detailed information about a CVD file:
     \begin{verbatim}
 zolw@localhost:/usr/local/share/clamav$ sigtool -i main.cvd
 Build time: 09 Jun 2006 22-19 +0200
 Version: 39
 # of signatures: 58116
 Functionality level: 8
 Builder: tkojm
 MD5: a9a400e70dcbfe2c9e11d78416e1c0cc
 Digital signature: 0s12V8OxLWO95fNNv+kTxj7CEWBW/1TKOGC7G4RelhogruBYw8dJeIX2+yhxex/XsLohxoEuXxC2CaFXiiTbrbvpK2USIxkpn53n6LYVV6jKgkP5sa08MdJE7cl29H1slfCrdaevBUZ1Z/UefkRnV6p3iQVpDPsBwqFRbrem33b
 Verification OK.
     \end{verbatim}
     There are two CVD databases in ClamAV: \emph{main.cvd} and \emph{daily.cvd}
     for daily updates.
 
     \section{Signature format}
 
     \subsection{MD5}
     There's an easy way to create signatures for static malware using MD5
     checksums. To create a signature for \verb+test.exe+ use the \verb+--md5+
     option of sigtool:
     \begin{verbatim}
 zolw@localhost:/tmp/test$ sigtool --md5 test.exe > test.hdb
 zolw@localhost:/tmp/test$ cat test.hdb 
 48c4533230e1ae1c118c741c0db19dfb:17387:test.exe
     \end{verbatim}
     That's it! The signature is ready to use:
     \begin{verbatim}
 zolw@localhost:/tmp/test$ clamscan -d test.hdb test.exe 
 test.exe: test.exe FOUND
 
 ----------- SCAN SUMMARY -----------
 Known viruses: 1
 Scanned directories: 0
 Engine version: 0.88.2
 Scanned files: 1
 Infected files: 1
 Data scanned: 0.02 MB
 Time: 0.024 sec (0 m 0 s)
     \end{verbatim}
     You can edit it to change the name (by default sigtool uses the file name).
     Remember that all MD5 signatures must be placed inside \verb+*.hdb+ files
     and you can include any number of signatures inside a single file. To get
     them automatically loaded every time clamscan/clamd starts just copy them
     to the local virus database directory.
 

     \subsection{MD5, PE section based}
     You can create an MD5 signature for a specific section in a PE file.
     Such signatures are stored in .mdb files in the following format:
     \begin{verbatim}
 PESectionSize:MD5:MalwareName
     \end{verbatim}
 

     \subsection{Hexadecimal signatures}
     ClamAV keeps viral fragments in hexadecimal format. If you don't know how
     to get a proper signature please try the MD5 method or submit your sample

     at \url{http://www.clamav.net/sendvirus}

 
     \subsubsection{Hexadecimal format}
     You can use \verb+sigtool --hex-dump+ to convert arbitrary data into
     hexadecimal format:
     \begin{verbatim}
 zolw@localhost:/tmp/test$ sigtool --hex-dump
 How do I look in hex?
 486f7720646f2049206c6f6f6b20696e206865783f0a
     \end{verbatim}
 
     \subsubsection{Wildcards}
     ClamAV supports the following extensions inside hex signatures:
     \begin{itemize}
 	\item \verb+??+\\
 	Match any byte.

 	\item \verb+a?+\\
 	Match high nibble (high four bits). \textbf{IMPORTANT NOTE:} Nibble
 	matching is only available in libclamav with the functionality level

 	17 therefore please only use it with .ndb signatures, each followed
 	by ":17" (MinEngineFunctionalityLevel, see \ref{ndb}).

 	\item \verb+?a+\\

 	Match low nibble (low four bits).

 	\item \verb+*+\\
 	Match any number of bytes.
 	\item \verb+{n}+\\
 	Match n bytes.
 	\item \verb+{-n}+\\
 	Match n or less bytes.
 	\item \verb+{n-}+\\
 	Match n or more bytes.
 	\item \verb+(a|b)+\\

 	Match a or b (you can use more alternate characters).

     \end{itemize}
 
     \subsubsection{Basic signature format}
     The simplest signatures are of the format:
     \begin{verbatim}
 MalwareName=HexSignature
     \end{verbatim}
     ClamAV will analyse a whole content of a file trying to match it. All
     signatures of this type must be placed in \verb+*.db+ files.
 

     \subsubsection{Extended signature format}\label{ndb}

     Extended signature format allows on including additional information about
     target file type, virus offset and required engine version.
     The format is:
     \begin{verbatim}
 MalwareName:TargetType:Offset:HexSignature[:MinEngineFunctionalityLevel:[Max]]
     \end{verbatim}
     where \verb+TargetType+ is one of the following decimal numbers describing
     the target file type:
     \begin{itemize}
 	\item 0 = any file
 	\item 1 = Portable Executable
 	\item 2 = OLE2 component (e.g. VBA script)
 	\item 3 = HTML (normalised)
 	\item 4 = Mail file
 	\item 5 = Graphics (to help catching exploits in JPEG files)
 	\item 6 = ELF
     \end{itemize}
     And	\verb+Offset+ is an asterisk or a decimal number \verb+n+ possibly
     combined with a special string:
     \begin{itemize}
 	\item \verb+*+ = any
 	\item \verb+n+ = absolute offset
 	\item \verb+EOF-n+ = end of file minus \verb+n+ bytes
     \end{itemize}
     Signatures for Portable Executables files (target = 1) also support:
     \begin{itemize}
 	\item \verb#EP+n# = entry point plus n bytes (\verb#EP+0# if you
 	want to anchor to \verb+EP+)
 	\item \verb#EP-n# = entry point minus n bytes

 	\item \verb#Sx+n# = start of section \verb+x+'s (counted from 0)

 	data plus \verb+n+ bytes

 	\item \verb#Sx-n# = start of section \verb+x+'s data minus \verb+n+ bytes

 	\item \verb#SL+n# = start of last section plus \verb+n+ bytes

 	\item \verb#SL-n# = start of last section minus \verb+n+ bytes

     \end{itemize}

     All the above offsets except \verb+*+ can be turned into
     \textbf{floating offsets} and represented as \verb+Offset,MaxShift+ where
     \verb+MaxShift+ is an unsigned integer. A floating offset will match every
     offset between \verb+Offset+ and \verb#Offset+MaxShift#, eg. \verb+10,5+
     will match all offsets from 10 to 15 and \verb#EP+n,y# will match all
     offsets from \verb#EP+n# to \verb#EP+n+y#. Versions of ClamAV older than
     0.91 will silently ignore the \verb+MaxShift+ extension and only use
     \verb+Offset+.\\
 
     All signatures in the extended format must be placed inside \verb+*.ndb+ files.

 
     \subsection{Signatures based on archive metadata}
     In order to detect some malware which spreads inside of Zip or RAR archives
     (especially encrypted ones) you can try to create a signature describing
     a malicious archived file. The general format is:
 \begin{verbatim}
 virname:encrypted:filename:normal size:csize:crc32:cmethod:fileno:max depth
 \end{verbatim}
     \begin{itemize}
 	\item Virus name
 	\item Encryption flag (1 -- encrypted, 0 -- not encrypted)
 	\item File name (* to ignore)
 	\item Normal (uncompressed) size (* to ignore)
 	\item Compressed size (* to ignore)
 	\item CRC32 (* to ignore)
 	\item Compression method (* to ignore)
 	\item File position in archive (* to ignore)
 	\item Maximum number of nested archives (* to ignore)
     \end{itemize}
     The database should have the extension \verb+.zmd+ or \verb+.rmd+ for
     Zip or RAR archive respectively.
 
     \subsection{Whitelist database}
     To whitelist a specific file use the MD5 signature format and place
     it in the database with the extension \verb+.fp+.
 
     \subsection{Signature names}
     ClamAV uses the following prefixes for particular malware:
     \begin{itemize}
 	\item \emph{Worm} for Internet worms
 	\item \emph{Trojan} for backdoor programs

 	\item \emph{Adware} for adware
 	\item \emph{Flooder} for flooders
         \item \emph{HTML} for HTML files
         \item \emph{Email} for email messages
         \item \emph{IRC} for IRC trojans

 	\item \emph{JS} for Java Script malware

 	\item \emph{PHP} for PHP malware
 	\item \emph{ASP} for ASP malware

 	\item \emph{VBS} for VBS malware

 	\item \emph{BAT} for BAT malware

 	\item \emph{W97M}, \emph{W2000M} for Word macro viruses
 	\item \emph{X97M}, \emph{X2000M} for Excel macro viruses
 	\item \emph{O97M}, \emph{O2000M} for general Office macro viruses
 	\item \emph{DoS} for Denial of Service attack software

 	\item \emph{DOS} for old DOS malware

 	\item \emph{Exploit} for popular exploits
 	\item \emph{VirTool} for virus construction kits
 	\item \emph{Dialer} for dialers
 	\item \emph{Joke} for hoaxes
     \end{itemize}

     Important rules of the naming convention:
     \begin{itemize}

 	\item always use a -zippwd suffix in the malware name for signatures of	      type zmd,
 	\item always use a -rarpwd suffix in the malware name for signatures

 	      of type rmd,
 	\item only use alphanumeric characters, dash (-), dot (.), underscores
 	      (\_) in malware names, never use space, apostrophe or quote mark.
     \end{itemize}

 
     \section{Special files}
 
     \subsection{HTML}
     ClamAV contains a special HTML normalisation code required to detect
     HTML exploits. Running \verb+sigtool --html-normalise+ on a HTML file
     should create the following files:
     \begin{itemize}
 	\item comment.html - the whole file normalised
 	\item nocomment.html - the file normalised, with all comments removed
 	\item script.html - the parts of the file in \verb+<script>+ tags
 	      (lowercased)
     \end{itemize}
     The code automatically decodes JScript.encode parts and char ref's (e.g.
     \verb+&#102;+). You need to create a signature against one of the created
     files. To eliminate potential false positive alerts you should use
     extended signature format with target type of 3.
 
     \subsection{Compressed Portable Executable files}
     If the file is compressed with UPX, FSG, Petite or other executable packer
     (supported by libclamav) run \verb+clamscan+ with
     \verb+--debug --leave-temps+. Example output on FSG compressed file:
     \begin{verbatim}
 LibClamAV debug: UPX/FSG: empty section found - assuming compression
 LibClamAV debug: FSG: found old EP @1554
 LibClamAV debug: FSG: Successfully decompressed
 LibClamAV debug: UPX/FSG: Decompressed data saved in /tmp/clamav-4eba73ff4050a26
     \end{verbatim}

     and then create a signature for \verb+/tmp/clamav-4eba73ff4050a26+

 
 \end{document}