=Paper=
{{Paper
|id=Vol-3017/demos99
|storemode=property
|title=Prototype Application to Detect Malicious Network Traffic with Case-based Reasoning and SEASALT
|pdfUrl=https://ceur-ws.org/Vol-3017/99.pdf
|volume=Vol-3017
|authors=Jakob M. Schoenborn,Klaus-Dieter Althoff
|dblpUrl=https://dblp.org/rec/conf/iccbr/SchoenbornA21
}}
==Prototype Application to Detect Malicious Network Traffic with Case-based Reasoning and SEASALT==
<pdf width="1500px">https://ceur-ws.org/Vol-3017/99.pdf</pdf>
<pre>
      Prototype application to detect malicious
    network traffic with case-based reasoning and
                     SEASALT

          Jakob M. Schoenborn1,2,3,* , Klaus-Dieter Althoff1,2
      1
       University of Hildesheim, Germany, schoenb@uni-hildesheim.de
    2
      German Research Center for Artificial Intelligence (DFKI), Germany,
                       klaus-dieter.althoff@dfki.de
          3
            Exploit Labs GmbH, Germany, jakob@exploitlabs.de

1    Introduction

The amount of criminal online activities rises. Protective measures such as fire-
walls and intrusion detection systems are being actively developed. We accom-
pany this development by offering a case-based reasoning prototype to detect
similar attacks based on previous cases. The instantiation of the SEASALT
framework allows us to distinguish between two different views on network traf-
fic: the request itself, and the traffic overall. Here, the focus has been set on
SQL-injections and cross site scripting - two of the most commonly used at-
tack vectors in the last decade1 . As we store cases containing these attacks, we
are able to detect slightly similar attacks, which would be difficult to detect,
for example, by a set of rules. Depending on the use-case, we identified up to
16 relevant attributes, predominantly text attributes. However, the similarity
assessment needs improvement to reduce the rate of false-positives.

2    Development of a prototype

Analyzing the network traffic data requires reliable tools to monitor the ongoing
network data. We gather the network data by using Wireshark2 and Burp3 .
Both aim to capture, filter, and adjust network traffic and are standard tools to
use in the domain, with slightly different foci. These tools allow us to generate
structured text data (CSV and XML), containing all relevant information to
automatically generate cases. Per default, seven columns are displayed: No.,
Time, Source, Destination, Protocol, Length, Info. Wireshark and Burp are the
standard tools for network analysis across many different institutions due to
their large variety of different observable protocols and continuing development
by volunteer contributions. Fig. 1 illustrates the general process of the system.
Every agent uses the myCBR4 3.0 SDK which is an open-source similarity-based
retrieval tool.
1
  see the OWASP Top10: https://owasp.org/www-project-top-ten/
2
  For more information, see https://www.wireshark.org/
3
  For more information, see https://portswigger.net/burp
4
  For more information, see http://mycbr-project.org/



Copyright © 2021 for this paper by its authors. Use permitted under
Creative Commons License Attribution 4.0 International (CC BY 4.0).
2       J. M. Schoenborn et al.




Fig. 1. Overview of the prototype. The workflow starts at index.jsp. By importing a
Wireshark or Burp Export, the corresponding agent will be initialized. Afterwards, the
user may send queries to the communication agent.


3    Experiment and Results
We distinguish between a normal and a malicious casebase. Initially, we fill
the normal casebase our agents with XML/CSV training imports, which do not
contain malicious traffic to establish a model of valid traffic. In a second step,
we fill the malicious casebases with hand-crafted malicious requests and public
lists of known SQLi/XSS attacks (‘payloads’) to establish a model of malicious
traffic. By using Burp and the OWASP Juice Shop, we are located in a controlled
environment without noisy data. In a third step, for training purposes, we import
a CSV or a XML file and search for malicious traffic.
    Our test is similar to the third step: We upload a XML file with six malicious
requests out of a total of 795 requests. These malicious requests are manually
created and are not part of the malicious casebase. We aim to automatically
identify the malicious requests after comparing each of the 795 requests against
cases in our malicious casebase. Basically, we query the CBR system automat-
ically for each request against the malicious casebase which has been trained
with malicious cases before. We expect to find similar cases with at least 90 %
similarity. Indeed, we can identify an attack containing:

    {‘email’:’ ’ AND INSERT INTO users VALUES(1,2,3,4); –’,’password’:’123’}.

    This attack revolves around guessing the number of columns the queued ta-
ble contains by adding numbers in the round brackets after VALUES, which is
a common testing approach. However, unfortunately, we only found one out of
six attacks. Lowering the threshold to at least 85 % similarity sheds light onto
the situation: now, we also do find more payloads which adds up to identifying
four out of six attacks. Nevertheless, we also find false-positives in 11/16 cases
(0,6875 %) and one redundant finding.

   More information in the video!
https://www.youtube.com/watch?v=XBJYp6GG4tM

</pre>