Abstract: Disclosed herein are an apparatus and method for constructing big data on unstructured cyber threat information. The method may include collecting unstructured cyber threat information, structuring the collected unstructured cyber threat information based on a previously trained AI model, and constructing big data from the structured cyber threat information.

Abstract: A network intrusion detection apparatus and method that perform Perl Compatible Regular Expressions (PCRE)-based pattern matching on the payloads of packets using a network processor equipped with a Deterministic Finite Automata (DFA) engine. The network intrusion detection apparatus includes a network processor core for receiving packets from a network, and transmitting payloads of the received packets to a Deterministic Finite Automata (DFA) engine. A detection rule converter converts a PCRE-based detection rule, preset to detect an attack packet, into a detection rule including a pattern to which only PCRE grammar corresponding to the DFA engine is applied. The DFA engine performs PCRE pattern matching on the payloads of the packets based on the detection rule converted by the detection rule converter.

Abstract: A system and method for detecting network intrusion by using a network processor are provided. The intrusion detection system includes: a first intrusion detector, configured to use a first network processor to perform intrusion detection on layer 3 and layer 4 of a protocol field among information included in a packet header of a packet transmitted to the intrusion detection system, and when no intrusion is detected, classify the packets according to stream and transmit the classified packets to a second intrusion detector; and a second intrusion detector, configured to use a second network processor to perform intrusion detection through deep packet inspection (DPI) for the packet payload of the packets transmitted from the first intrusion detector. Thereby, intrusion detection for high-speed packets can be performed in a network environment.

Abstract: A network intrusion detection apparatus and method that perform Perl Compatible Regular Expressions (PCRE)-based pattern matching on the payloads of packets using a network processor equipped with a Deterministic Finite Automata (DFA) engine. The network intrusion detection apparatus includes a network processor core for receiving packets from a network, and transmitting payloads of the received packets to a Deterministic Finite Automata (DFA) engine. A detection rule converter converts a PCRE-based detection rule, preset to detect an attack packet, into a detection rule including a pattern to which only PCRE grammar corresponding to the DFA engine is applied. The DFA engine performs PCRE pattern matching on the payloads of the packets based on the detection rule converted by the detection rule converter.

Abstract: The present invention relates to a network management system for analyzing Internet application traffic. An apparatus for Internet application traffic classification benchmark according to the present invention configures two or more Internet application traffic classifications in plug-in scheme to perform a benchmarking function for the performance of each Internet application traffic classification. The apparatus can provide an objective and accurate evaluation for each classification technology by aggregating various Internet application traffic classification technologies by the plug-in scheme.

Abstract: A system and method for detecting network intrusion by using a network processor are provided. The intrusion detection system includes: a first intrusion detector, configured to use a first network processor to perform intrusion detection on layer 3 and layer 4 of a protocol field among information included in a packet header of a packet transmitted to the intrusion detection system, and when no intrusion is detected, classify the packets according to stream and transmit the classified packets to a second intrusion detector; and a second intrusion detector, configured to use a second network processor to perform intrusion detection through deep packet inspection (DPI) for the packet payload of the packets transmitted from the first intrusion detector. Thereby, intrusion detection for high-speed packets can be performed in a network environment.

Abstract: The present invention relates to a network management system for analyzing Internet application traffic. An apparatus for Internet application traffic classification benchmark according to the present invention configures two or more Internet application traffic classifications in plug-in scheme to perform a benchmarking function for the performance of each Internet application traffic classification. The apparatus can provide an objective and accurate evaluation for each classification technology by aggregating various Internet application traffic classification technologies by the plug-in scheme.