Accelerating firewall through intelligent self-learning

A new approach to increase the throughput of firewall is proposed. Packet filtering and connection management usually done in firewall are relocated to the proposed firewall accelerator engine, named FA. FA also learns the behavior of firewall in an intelligent and unique way. With the knowledge acquired by the self-learning, FA can significantly reduce the number of packets to be fed to firewall and let firewall focus on content filtering that is widely used for protecting the Internet hackings. Some empirical studies show the proposed without changing the existing (or guessing) network configuration.