AIEngine is a next-generation interactive/programmable Python/Ruby/Java/Lua and Go network intrusion detection system engine with capabilities of learning without any human intervention, DNS domain classification, Spam detection, network collector, network forensics and many others.

It also helps network/security professionals to identify traffic and develop signatures for using them on NIDS, Firewalls, Traffic classifiers and so on.

The main functionalities of AIEngine are:

• Support for interacting/programming with the user while the engine is running.
• Support for PCRE JIT for regex matching.
• Support for regex graphs (complex detection patterns).
• Support five types of NetworkStacks (lan,mobile,lan6,virtual and oflow).
• Support Sets and Bloom filters for IP searches.
• Supports x86_64, ARM and MIPS architecture over operating systems such as Linux, FreeBSD and MacOS.
• Support for HTTP,DNS and SSL Domains matching.
• Support for banned domains and hosts for HTTP, DNS, SMTP and SSL.
• Frequency analysis for unknown traffic and auto-regex generation.
• Generation of Yara signatures.
• Easy integration with databases (MySQL, Redis, Cassandra, Hadoop, etc...) for data correlation.
• Easy integration with other packet engines (Netfilter).
• Support memory clean caches for refresh stored memory information.
• Support for detect DDoS at network/application layer.
• Support for rejecting TCP/UDP connections.
• Support for network forensics on real time.
• Supports protocols such as Bitcoin, CoAP, DHCPv4/DHCPv6, DNS, GPRS, GRE, HTTP, ICMPv4/ICMPv6, IMAP, IPv4/v6, Modbus, MPLS, MQTT, Netbios, NTP, OpenFlow, PPPoE, POP, Quic, RTP, SIP, SMB, SMTP, SSDP, SSH, SSL, TCP, UDP, VLAN, VXLAN.

Using AIEngine

To use AIEngine (reduce version) just execute the binary aiengine or use the python/ruby/java/lua binding.

luis@luis-xps:~/c++/aiengine/src$ ./aiengine -h
 aiengine 1.8.0
 Mandatory arguments:
   -I [ --input ] arg                Sets the network interface ,pcap file or
                                     directory with pcap files.
 
 Link Layer optional arguments:
   -q [ --tag ] arg      Selects the tag type of the ethernet layer (vlan,mpls).
 
 TCP optional arguments:
   -t [ --tcp-flows ] arg (=32768) Sets the number of TCP flows on the pool.
 
 UDP optional arguments:
   -u [ --udp-flows ] arg (=16384) Sets the number of UDP flows on the pool.
 
 Regex optional arguments:
   -R [ --enable-signatures ]     Enables the Signature engine.
   -r [ --regex ] arg (=.*)       Sets the regex for evaluate agains the flows.
   -c [ --flow-class ] arg (=all) Uses tcp, udp or all for matches the signature
                  on the flows.
   -m [ --matched-flows ]         Shows the flows that matchs with the regex.
   -M [ --matched-packet ]        Shows the packet payload that matchs with
                                  the regex.
   -C [ --continue ]              Continue evaluating the regex with the
                                  next packets of the Flow.
   -j [ --reject-flows ]          Rejects the flows that matchs with the
                                      regex.
   -w [ --evidence ]              Generates a pcap file with the matching
                                      regex for forensic analysis.
 
 Frequencies optional arguments:
   -F [ --enable-frequencies ]       Enables the Frequency engine.
   -g [ --group-by ] arg (=dst-port) Groups frequencies by src-ip,dst-ip,src-por
                     t and dst-port.
   -f [ --flow-type ] arg (=tcp)     Uses tcp or udp flows.
   -L [ --enable-learner ]           Enables the Learner engine.
   -k [ --key-learner ] arg (=80)    Sets the key for the Learner engine.
   -b [ --buffer-size ] arg (=64)    Sets the size of the internal buffer for
                                     generate the regex.
       -Q [ --byte-quality ] arg (=80)   Sets the minimum quality for the bytes of
                                         the generated regex.
   -y [ --enable-yara ]              Generates a yara signature.
 
 
 Optional arguments:
   -n [ --stack ] arg (=lan)    Sets the network stack (lan,mobile,lan6,virtual,
                    oflow).
   -d [ --dumpflows ]           Dump the flows to stdout.
   -s [ --statistics ] arg (=0) Show statistics of the network stack (5 levels).
   -T [ --timeout ] arg (=180)  Sets the flows timeout.
   -P [ --protocol ] arg        Show statistics of a specific protocol of the
                                    network stack.
   -e [ --release ]             Release the caches.
   -l [ --release-cache ] arg   Release a specific cache.
   -p [ --pstatistics ]         Show statistics of the process.
       -o [ --summary ]             Show protocol summmary statistics
                                    (bytes,packets,% bytes,cache miss,memory).
   -h [ --help ]                Show help.
   -v [ --version ]             Show version string.

NetworkStack Types

AIEngine supports five types of Network stacks depending on the network topology.

• StackLan (LAN) Local Area Network based on IPv4.
• StackLanIPv6 (lan6) Local Area Network with IPv6 support.
• StackMobile (mobile) Network Mobile (Gn interface) for IPv4.
• StackVirtual (virtual) Stack for virtual/cloud environments with VxLan and GRE Transparent.
• StackOpenFlow (oflow) Stack for OpenFlow environments.