adulau/pdns-qof
1
0
Fork 0
mirror of https://github.com/adulau/pdns-qof.git synced 2024-11-25 03:27:10 +00:00
Code Issues Projects Releases Packages Wiki Activity
pdns-qof/to-submit/draft-dulaunoy-kaplan-passive-dns-cof-00.xml

412 lines
22 KiB
XML
Raw Permalink Normal View History

00 submitted
2013-12-27 16:48:02 +00:00
<?xml version="1.0" encoding="US-ASCII"?>
<!-- This template is for creating an Internet Draft using xml2rfc,
which is available here: http://xml.resource.org. -->
<!DOCTYPE rfc SYSTEM "rfc2629.dtd" [
<!-- One method to get references from the online citation libraries.
There has to be one entity for each item to be referenced.
An alternate method (rfc include) is described in the references. -->
<!ENTITY RFC2119 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.2119.xml">
<!ENTITY RFC2629 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.2629.xml">
<!ENTITY RFC3552 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.3552.xml">
<!ENTITY RFC1035 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.1035.xml">
<!ENTITY RFC1034 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.1034.xml">
<!ENTITY RFC4627 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.4627.xml">
<!ENTITY RFC5001 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.5001.xml">
<!ENTITY RFC3597 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.3597.xml">
<!ENTITY RFC3912 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.3912.xml">
<!ENTITY RFC6648 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.6648.xml">
<!ENTITY RFC2234 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.2234.xml">
<!ENTITY RFC6973 SYSTEM "http://xml.resource.org/public/rfc/bibxml/reference.RFC.6973.xml">
<!ENTITY I-D.narten-iana-considerations-rfc2434bis SYSTEM "http://xml.resource.org/public/rfc/bibxml3/reference.I-D.narten-iana-considerations-rfc2434bis.xml">
<!-- <!ENTITY I-D.draft-bortzmeyer-dnsop-dns-privacy SYSTEM "http://xml.resource.org/public/rfc/bibxml3/reference.I-D.draft-bortzmeyer-dnsop-dns-privacy"> TO ENABLE when bibxml3 is back to normal -->
]>
<?xml-stylesheet type='text/xsl' href='rfc2629.xslt' ?>
<!-- used by XSLT processors -->
<!-- For a complete list and description of processing instructions (PIs),
please see http://xml.resource.org/authoring/README.html. -->
<!-- Below are generally applicable Processing Instructions (PIs) that most I-Ds might want to use.
(Here they are set differently than their defaults in xml2rfc v1.32) -->
<?rfc strict="yes" ?>
<!-- give errors regarding ID-nits and DTD validation -->
<!-- control the table of contents (ToC) -->
<?rfc toc="yes"?>
<!-- generate a ToC -->
<?rfc tocdepth="4"?>
<!-- the number of levels of subsections in ToC. default: 3 -->
<!-- control references -->
<?rfc symrefs="yes"?>
<!-- use symbolic references tags, i.e, [RFC2119] instead of [1] -->
<?rfc sortrefs="yes" ?>
<!-- sort the reference entries alphabetically -->
<!-- control vertical white space
(using these PIs as follows is recommended by the RFC Editor) -->
<?rfc compact="yes" ?>
<!-- do not start each main section on a new page -->
<?rfc subcompact="no" ?>
<!-- keep one blank line between list items -->
<!-- end of list of popular I-D processing instructions -->
<rfc category="info" docName="draft-dulaunoy-kaplan-passive-dns-cof-00" ipr="trust200902">
<!-- category values: std, bcp, info, exp, and historic
ipr values: full3667, noModification3667, noDerivatives3667
you can add the attributes updates="NNNN" and obsoletes="NNNN"
they will automatically be output with "(if approved)" -->
<!-- ***** FRONT MATTER ***** -->
<front>
<title abbrev="Passive DNS - Common Output Format">Passive DNS - Common Output Format</title>
<author fullname="Alexandre Dulaunoy" initials="A."
surname="Dulaunoy">
<organization>CIRCL</organization>
<address>
<postal>
<street>41, avenue de la gare</street>
<city>Luxembourg</city>
<region></region>
<code>L-1611</code>
<country>Luxembourg</country>
</postal>
<phone>(+352) 247 88444</phone>
<email>alexandre.dulaunoy@circl.lu</email>
<uri>http://www.circl.lu/</uri>
<!-- uri and facsimile elements may also be added -->
</address>
</author>
<author fullname="L. Aaron Kaplan" initials="A."
surname="Kaplan">
<organization>CERT.at</organization>
<address>
<postal>
<street>Karlsplatz 1/2/9</street>
<city>Vienna</city>
<region></region>
<code>A-1010</code>
<country>Austria</country>
</postal>
<phone>+43 1 5056416 78</phone>
<email>kaplan@cert.at</email>
<uri>http://www.cert.at/</uri>
</address>
</author>
<author fullname="Paul Vixie" initials="P."
surname="Vixie">
<organization>Farsight Security, Inc.</organization>
<address>
<postal>
<street>11400 La Honda Road</street>
<city>Woodside</city>
<region>California</region>
<code>94062</code>
<country>U.S.A.</country>
</postal>
<phone></phone>
<email>paul@redbarn.org</email>
<uri>https://www.farsightsecurity.com/</uri>
</address>
</author>
<author fullname="Henry Stern" initials="H." surname="Stern">
<organization>Farsight Security, Inc.</organization>
<address>
<postal>
<street>1741 Brunswick Street, Suite 500</street>
<city>Halifax</city>
<region>Nova Scotia</region>
<code>B3J 3X8</code>
<country>Canada</country>
</postal>
<phone>+1 408 922 4555</phone>
<email>stern@fsi.io</email>
<uri>https://www.farsightsecurity.com/</uri>
</address>
</author>
<date month="December" year="2013" />
<area>General</area>
<workgroup>Internet Engineering Task Force</workgroup>
<keyword>dns</keyword>
<abstract>
<t>This document describes a common output format of Passive DNS Servers which clients can query. The output format description includes also in addition a common semantic for each Passive DNS system. By having multiple Passive DNS Systems adhere to the same output format for queries, users of multiple Passive DNS servers will be able to combine result sets easily.</t>
</abstract>
</front>
<middle>
<section title="Introduction">
<t>Passive DNS is a technique described by Florian Weimer in 2005 in <xref target="WEINERPDNS">Passive DNS replication, F Weimer - 17th Annual FIRST Conference on Computer Security</xref>. Since then multiple Passive DNS implementations were created and evolved over time. Users of these Passive DNS servers may query a server (often via <xref target="RFC3912">WHOIS</xref> or HTTP <xref target="REST">REST</xref>), parse the results and process them in other applications.</t>
<t>
There are multiple implementations of Passive DNS software. Users of passive DNS query each implementation and aggregate the results for their search. This document describes the output format of four Passive DNS Systems (<xref target="DNSDB"/>, <xref target="PDNSCERTAT"/>, <xref target="PDNSCIRCL"/> and <xref target="PDNSCOF"/>) which are in use today and which already share a nearly identical output format.
As the format and the meaning of output fields from each Passive DNS need to be consistent, we propose in this document a solution to commonly name each field along with their corresponding interpretation. The format follows a simple key-value structure in <xref target="RFC4627">JSON</xref> format.
The benefit of having a consistent Passive DNS output format is that multiple client implementations can query different servers without having to have a separate parser for each
individual server. <xref target="PDNSCLIENT">passivedns-client</xref> currently implements multiple parsers due to a lack of standardization.
The document does not describe the protocol (e.g. <xref target="RFC3912">WHOIS</xref>, HTTP <xref target="REST">REST</xref>) nor the query format used to query the Passive DNS. Neither does this document describe "pre-recursor" Passive DNS Systems. Both of these are separate topics and deserve their own RFC document.
</t>
<section title="Requirements Language">
<t>The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
document are to be interpreted as described in <xref
target="RFC2119">RFC 2119</xref>.</t>
</section>
</section>
<section title="Limitation">
<t> As a Passive DNS servers can include protection mechanisms for their operation, results might be different due to those protection measures. These mechanisms filter out DNS answers if they fail some criteria. The <xref target="BAILIWICK">bailiwick algorithm</xref> protects the Passive DNS Database from <xref target="CACHEPOISONING">cache poisoning attacks</xref>.
Another limitation that clients querying the database need to be aware of is that each query simply gets a snapshot-answer of the time of querying. Clients MUST NOT rely on consistent answers. Nor must they assume that answers must be identical across multiple Passive DNS Servers.
</t>
</section>
<section title="Common Output Format">
<section title="Overview">
<t>The formatting of the answer follows the <xref target="RFC4627">JSON</xref> format. The order of the fields is not significant for the same resource type. </t>
<t>The intent of this output format is to be easily parsable by scripts. Each JSON object is expressed on a single line to be processed by the client line-by-line. Every implementation MUST support the JSON output format.</t> <!-- note: it is "parsable" if you want to be really nit-picking. See: https://en.wiktionary.org/wiki/parsable -->
<t><xref target="app-additional">Examples of JSON</xref> output are in the appendix.</t>
</section>
<section title="ABNF grammar">
<figure><preamble>Formal grammar as defined in <xref target="RFC2234">ABNF</xref></preamble><artwork><![CDATA[
answer = entries
entries = * ( entry CR)
entry = "{" keyvallist "}"
keyvallist = [ member *( value-separator member ) ]
member = field name-separator value
name-separator = ws %x3A ws ; : colon
value = value ; as defined in the JSON RFC
field = "rrame" | "rrtype" | "rdata" | "time_first" |
"time_last" | "count" | "bailiwick" | "sensor_id" |
"zone_time_first" | "zone_time_last" | futureField
futureField = string
CR = %x0D
]]></artwork></figure>
<t>Note that value is defined in <xref target="RFC4627">JSON</xref> and has the exact same specification as there. The same goes for the definition of string.</t>
</section>
<section title="Mandatory Fields">
<t>Implementation MUST support all the mandatory fields.</t>
<t>Uniqueness property: the tuple (rrname,rrtype,rdata) will always be unique within one answer per server. While rrname and rrtype are always individual JSON primitive types (strings, numbers, booleans or null), rdata MAY be an array as defined in <xref target="RFC4627">JSON</xref>. Implementors of this draft MUST be able to deal with rdata being returned as JSON array or alternatively as a JSON string. <!-- MOTE: this is not good --></t>
<section title="rrname">
<t>This field returns the name of the queried resource.</t>
</section>
<section title="rrtype">
<t>This field returns the resource record type as seen by the passive DNS. The key is rrtype and the value is in the interpreted record type. If the value cannot be interpreted the
decimal value is returned following the principle of transparency as described in <xref target="RFC3597">RFC 3597</xref>.
The resource record type can be any values as described by IANA in the DNS parameters document in the section 'DNS Label types' (http://www.iana.org/assignments/dns-parameters).
Currently known and supported textual descriptions of rrtypes are: A, AAAA, CNAME, PTR, SOA, TXT, DNAME, NS, SRV, RP, NAPTR, HINFO, A6.
A client MUST be able to understand these textual rtype values. In addition, a client MUST be able to handle a decimal value (as mentioned above) as answer.
</t>
</section>
<section title="rdata">
<t>This field returns the data of the queried resource. In general, this is to be interpreted as string. Depending on the rtype, this can be an IPv4 or IPv6 address, a domain name (as in the case of CNAMEs), an SPF record, etc. A client MUST be able to interpret any value which is legal as the right hand side in a DNS zone file <xref target="RFC1035">RFC 1035</xref> and <xref target="RFC1034">RFC 1034</xref>. If the rdata came from an unknown DNS resource records, the server must follow the transparency principle as described in <xref target="RFC3597">RFC 3597</xref>.</t>
</section>
<section title="time_first">
<t>This field returns the first time that the record / unique tuple (rrname, rrtype, rdata) has been seen by the passive DNS. The date is expressed in seconds (decimal ASCII) since 1st of January 1970 (Unix timestamp). The time zone MUST be UTC.</t>
</section>
<section title="time_last">
<t>This field returns the last time that the unique tuple (rrname, rrtype, rdata) record has been seen by the passive DNS. The date is expressed in seconds (decimal ASCII) since 1st of January 1970 (Unix timestamp). The time zone MUST be UTC.</t>
</section>
</section>
<section title="Optional Fields">
<t>Implementations SHOULD support one or more fields.</t>
<section title="count">
<t>Specifies how many authoritative DNS answers were received at the Passive DNS Server's collectors with exactly the given set of values as answers (i.e. same data in the answer set - compare with the uniqueness property in "Mandatory Fields"). The number of requests is expressed as a decimal value.</t>
</section>
<section title="bailiwick">
<t>The bailiwick is the best estimate of the apex of the zone where this data is authoritative. String.</t>
</section>
</section>
<section title="Additional Fields">
<t>Implementations MAY support the following fields:</t>
<section title="sensor_id">
<t>This field returns the sensor information where the record was seen. The sensor_id is an opaque byte string as defined by <xref target="RFC5001"> RFC 5001 in section 2.3</xref>.</t>
</section>
<section title="zone_time_first">
<t>This field returns the first time that the unique tuple (rrname, rrtype, rdata) record has been seen via zone file import. The date is expressed in seconds (decimal ASCII) since 1st of January 1970 (Unix timestamp). The time zone MUST be UTC.</t>
</section>
<section title="zone_time_last">
<t>This field returns the last time that the unique tuple (rrname, rrtype, rdata) record has been seen via zone file import. The date is expressed in seconds (decimal ASCII) since 1st of January 1970 (Unix timestamp). The time zone MUST be UTC.</t>
</section>
</section>
<section title="Additional Fields Registry">
<t>In accordance with <xref target="RFC6648"/>, designers of new passive DNS applications that would need additional fields can request and register new field name at https://github.com/adulau/pdns-qof/wiki/Additional-Fields.</t>
</section>
</section>
<!-- This PI places the pagebreak correctly (before the section title) in the text output. -->
<?rfc needLines="8" ?>
<section anchor="Acknowledgements" title="Acknowledgements">
<t>Thanks to the Passive DNS developers who contributed to the document.</t>
</section>
<!-- Possibly a 'Contributors' section ... -->
<section anchor="IANA" title="IANA Considerations">
<t>This memo includes no request to IANA.</t>
</section>
<section anchor="Privacy" title="Privacy Considerations">
<t>Passive DNS Servers capture DNS answers from multiple collecting points ("sensors") which are located on the Internet-facing side of DNS recursors ("post-recursor passive DNS"). In this process, they intentionally omit the source IP, source port, destination IP and destination port from the captured packets. Since the data is captured "post-recursor", the timing information (who queries what) is lost, since the recursor will cache the results. Furthermore, since multiple sensors feed into a passive DNS server, the resulting data gets mixed together, reducing the likelihood that Passive DNS Servers are able to find out much about the actual person querying the DNS records nor who actually sent the query. In this sense, passive DNS Servers are similar to keeping an archive of all previous phone books - if public DNS records can be compared to phone numbers - as they often are.
Nevertheless, the authors strongly encourage Passive DNS implementors to take special care of privacy issues. [draft-bortzmeyer-dnsop-dns-privacy] is an excellent starting point for this.
Finally, the overall recommendations in <xref target="RFC6973">RFC6973</xref> should be taken into consideration when designing any application which uses Passive DNS data.</t>
</section>
<section anchor="Security" title="Security Considerations">
<t>In some cases, Passive DNS output might contain confidential information and its access might be restricted. When a user is querying multiple Passive DNS and aggregating the data, the sensitivity of the data must be considered.</t>
</section>
</middle>
<!-- *****BACK MATTER ***** -->
<back>
<!-- References split into informative and normative -->
<!-- There are 2 ways to insert reference entries from the citation libraries:
1. define an ENTITY at the top, and use "ampersand character"RFC2629; here (as shown)
2. simply use a PI "less than character"?rfc include="reference.RFC.2119.xml"?> here
(for I-Ds: include="reference.I-D.narten-iana-considerations-rfc2434bis.xml")
Both are cited textually in the same manner: by using xref elements.
If you use the PI option, xml2rfc will, by default, try to find included files in the same
directory as the including file. You can also define the XML_LIBRARY environment variable
with a value containing a set of directories to search. These can be either in the local
filing system or remote ones accessed by http (http://domain/dir/... ).-->
<references title="Normative References">
<!--?rfc include="http://xml.resource.org/public/rfc/bibxml/reference.RFC.2119.xml"?-->
&RFC2119;
&RFC1035;
&RFC1034;
&RFC3912;
&RFC4627;
&RFC5001;
&RFC3597;
&RFC6648;
&RFC2234;
&RFC6973;
</references>
<references>
<reference anchor="WEINERPDNS" target="http://www.enyo.de/fw/software/dnslogger/first2005-paper.pdf">
<front>
<title>Passive DNS Replication</title>
<author fullname="Florian Weimer"/>
<date year="2005"/>
</front>
</reference>
<reference anchor="CACHEPOISONING" target="http://kurser.lobner.dk/dDist/DMK_BO2K8.pdf">
<front>
<title>Black ops 2008: It&#8217;s the end of the cache as we know it.</title>
<author fullname="Dan Kaminsky"/>
<date year="2008"/>
</front>
</reference>
<reference anchor="BAILIWICK" target="https://archive.farsightsecurity.com/Passive_DNS/passive_dns_hardening_handout.pdf">
<front>
<title>Passive DNS Hardening</title>
<author fullname="Robert Edmonds"/>
<date year="2010"/>
</front>
</reference>
<reference anchor="PDNSCLIENT" target="https://github.com/chrislee35/passivedns-client">
<front>
<title>Queries 5 major Passive DNS databases: BFK, CERTEE, DNSParse, ISC, and VirusTotal.</title>
<author fullname="Chris Lee"/>
<date year="2013"/>
</front>
</reference>
<reference anchor="REST" target="http://www.ics.uci.edu/~fielding/pubs/dissertation/rest_arch_style.htm">
<front>
<title>Representational State Transfer (REST)</title>
<author fullname="Roy Thomas Fielding"/>
<date year="2000"/>
</front>
</reference>
<reference anchor="DNSDB" target="https://api.dnsdb.info/">
<front>
<title>DNSDB API</title>
<author fullname="Farsight Security"/>
<date year="2013"/>
</front>
</reference>
<reference anchor="PDNSCERTAT" target="http://www.centr.org/system/files/agenda/attachment/rd4-papst-passive_dns.pdf">
<front>
<title>pDNS presentation at 4th Centr R&amp;D workshop Frankfurt Jun 5th 2012</title>
<author fullname="CERT.at"/>
<date year="2012"/>
</front>
</reference>
<reference anchor="PDNSCIRCL" target="http://pdns.circl.lu/">
<front>
<title>CIRCL Passive DNS</title>
<author fullname="CIRCL -Computer Incident Response Center Luxembourg"/>
<date year="2012"/>
</front>
</reference>
<reference anchor="PDNSCOF" target="https://github.com/adulau/pdns-qof-server/">
<front>
<title>Passive DNS server interface using the common output format</title>
<author fullname="Alexandre Dulaunoy"/>
<date year="2013"/>
</front>
</reference>
</references>
<references title="Informative References">
<!-- Here we use entities that we defined at the beginning. -->
&RFC3552;
&I-D.narten-iana-considerations-rfc2434bis;
<!-- &I-D.draft-bortzmeyer-dnsop-dns-privacy; -->
</references>
<section anchor="app-additional" title="Examples">
<t>If you query a passive DNS for the rrname www.ietf.org, the passive dns common output format can be:</t>
<figure><artwork>
<![CDATA[
{"count": "37", "time_first": "1384865833", "rrtype": "A",\
"rrname": "www.ietf.org", "rrdata": "4.31.198.44",\
"time_last": "1388132830"}
{"count": "102", "time_first": "1298412391", "rrtype": "AAAA",\
"rrname": "www.ietf.org", "rrdata": "2001:1890:1112:1::20",\
"time_last": "1302506851"}
]]>
</artwork></figure>
<t>If you query a passive DNS for the rrname ietf.org, the passive dns common output format can be:</t>
<figure><artwork>
<![CDATA[
{"count": "4", "time_first": "1298495035", "rrtype": "A",\
"rrname": "ietf.org", "rrdata": "64.170.98.32",\
"time_last": "1298495035"}
{"count": "109330", "time_first": "1298398002", "rrtype": "NS",\
"rrname": "ietf.org", "rrdata": "ns1.yyz1.afilias-nst.info",\
"time_last": "1388134770"}
{"count": "9", "time_first": "1317037550", "rrtype": "AAAA",\
"rrname": "ietf.org", "rrdata": "2001:1890:123a::1:1e",\
"time_last": "1330209752"}
]]>
</artwork></figure>
</section>
</back>
</rfc>
Reference in a new issue Copy permalink