Title :
A high throughput parallel architecture for category specific Deep Packet Inspection
Author :
Sananda, Velacheri Jagadeesan
Author_Institution :
Lone Star Design Center, Austin, TX, USA
Abstract :
This paper describes a Field Programmable Gate Array hardware based Deep Packet Inspection Engine that uses regular expression matchers to simultaneously categorize and look for malicious signatures in Ethernet packets. This was a submission to the 2010 MEMOCODE Design Contest. It is the fastest Xilinx FPGA based design with a throughput of 734 Mbit/sec and the 2nd fastest overall, out of all designs submitted from teams worldwide. A unique feature of this architecture is that the high throughput is independent of both the number of categorizers and the density of malicious signatures.
Keywords :
computer viruses; field programmable gate arrays; inspection; local area networks; parallel architectures; 2010 MEMOCODE Design Contest; Ethernet packets; FPGA; deep packet inspection engine; field programmable gate array; malicious signatures; parallel architecture; regular expression matchers; throughput; Computer architecture; Engines; Field programmable gate arrays; Hardware; IP networks; Inspection; Throughput;
Conference_Titel :
Formal Methods and Models for Codesign (MEMOCODE), 2010 8th IEEE/ACM International Conference on
Conference_Location :
Grenoble
Print_ISBN :
978-1-4244-7885-9
Electronic_ISBN :
978-1-4244-7886-6
DOI :
10.1109/MEMCOD.2010.5558647