BLATTA: Early Exploit Detection on Network Traffic with Recurrent Neural Networks

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Number of TCP connections</td><td class="align_center">5687</td></tr><tr><td class="align_left">Protocols</td><td class="align_center">HTTP (3857), FTP (6), SMTP (74), POP3 (93)</td></tr><tr><td class="align_left">Payload types</td><td class="align_center">JavaScript, shellcode, Perl, PHP, Python, Ruby, Bash, SQL</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr><tr class="table-fn"><td><div><i>Note</i>. The numbers next to the protocols are the number of connections in the application layer protocols.<br/></div></td></tr></table>

<div>A summary of exploits captured in the BlattaSploit dataset.</div>

Security and Communication Networks

tab2

Table 2

Table 2: BLATTA: Early Exploit Detection on Network Traffic with Recurrent Neural Networks 