摘要:
A detection device (10) identifies candidate bots using flow data. The detection device (10) uses the flow data to count the number of candidate bots communicating with each server and determines a server communicating with a predetermined number or more of candidate bots as a malicious server. The detection device (10) detects a candidate bot communicating with the malicious server as a malicious bot.
摘要:
A detection device (100) generates an event sequence from events that are acquired for each of identifiers that distinguish among terminals in a monitoring target network or pieces of malware, by taking into account an order of occurrence of the events. The detection device (100) retrieves events that commonly occur in event sequences belonging to a same cluster among clusters including event sequences with similarities at a predetermined level or higher, and extracts, as a detection event sequence, a representative event sequence based on a relationship between events that have high occurrence rates in similar common event sequences. The detection device (100) detects a malware infected terminal in the monitoring target network based on whether the event sequence generated based on a communication in the monitoring target network and the extracted detection event sequence match each other.
摘要:
A flow information analysis apparatus (10) receives flow information containing a header sample, determines whether the header sample of the flow information matches any of templates that are based on tunneling protocols, and when determining that the header sample matches any of the templates, extract information on a header of the IP packet from the header sample on the basis of the matched template. Further, when determining that the header sample does not match any of the templates, the flow information analysis apparatus (10) extracts information on the header of the IP packet from the header sample on the basis of a result of a search through the header sample for a byte sequence that matches search data in which a value that is set in a specific field of the tunnel header and a value that is set in a specific field of the IP packet are combined.
摘要:
A malicious communication pattern extraction device (10) includes a statistical value calculation unit (132) that calculates a statistical value for an appearance frequency of each of a plurality of communication patterns that is a combination of a field and a value, from a traffic log (31) obtained from the traffic caused by malware, and a traffic log (21) obtained from traffic in a predetermined communication environment; a malicious list candidate extraction unit (134) that compares between the appearance frequency of the traffic log (21) and the appearance frequency of the traffic log (31) for each of the communication patterns, based on the statistical value calculated by the statistical value calculation unit (132), and extracts the communication pattern as the malicious communication pattern when a difference between both of the appearance frequencies is equal to or more than a predetermined threshold; and a threshold setting unit (135) that sets a threshold so that an erroneous detection rate being probability of erroneously detecting the traffic caused by malware is equal to or less than a certain value as well as a detection rate that is probability of detecting the traffic caused by malware is equal to or more than a certain value.
摘要:
A malicious communication pattern extraction device (10) includes a statistical value calculation unit (132) that calculates a statistical value for an appearance frequency of each of a plurality of communication patterns that is a combination of a field and a value, from a traffic log (31) obtained from the traffic caused by malware, and a traffic log (21) obtained from traffic in a predetermined communication environment; a malicious list candidate extraction unit (134) that compares between the appearance frequency of the traffic log (21) and the appearance frequency of the traffic log (31) for each of the communication patterns, based on the statistical value calculated by the statistical value calculation unit (132), and extracts the communication pattern as the malicious communication pattern when a difference between both of the appearance frequencies is equal to or more than a predetermined threshold; and a threshold setting unit (135) that sets a threshold so that an erroneous detection rate being probability of erroneously detecting the traffic caused by malware is equal to or less than a certain value as well as a detection rate that is probability of detecting the traffic caused by malware is equal to or more than a certain value.
摘要:
A search apparatus (10) extracts fingerprints that are combinations of first communication data corresponding to requests and second communication data corresponding to responses to the requests from communication data of known malware independently from protocols. The search apparatus 10 gives degrees of priority corresponding to degrees of maliciousness of the malware, to the fingerprints. The search apparatus (10) decides search-target sending-out destinations from among sending-out destinations. The search apparatus (10) generates probes based on the first communication data of the fingerprints and signatures based on payloads of the second communication data of the fingerprints. The search apparatus (10) sends out the probes to the search-target sending-out destinations in order according to the degrees of priority. The search apparatus (10) determines whether the sending-out destinations are malicious or not based on responses and the signatures.
摘要:
A classification apparatus 10 acquires a communication log including a plurality of pieces of traffic data, and extracts different types of feature values from the plurality of pieces of traffic data. Subsequently, the classification apparatus 10 classifies the traffic data on a per IP address basis based on the extracted different types of feature values, and uses a plurality of classification results to count the number of times of appearance of a pattern having the same combination of the classification results.
摘要:
A blacklist generating device (300) acquires a malicious communication log (301a) and a normal communication log (301b). A malicious communication profile extracting function (305) calculates statistics on communication patterns included in the malicious communication log (301a) and outputs a communication pattern satisfying a certain condition to a potential blacklist (305a). A normal communication profile extracting function (306) calculates statistics on communication patterns included in the normal communication log (301b) and outputs a communication pattern satisfying a certain condition to a whitelist (306a). A blacklist creating function (307) searches the potential blacklist (305a) for a value with the value on the whitelist (306a), excludes a coincident communication pattern from the potential blacklist (305a), and creates a blacklist (307a).
摘要:
There is provided an analysis rule adjustment device that adjusts an analysis rule used in a communication log analysis performed to detect malicious communication through a network. The analysis rule adjustment device includes a log acquisition unit, a log analysis unit, and a first analysis unit. The log acquisition unit acquires a communication log through a network to be defended and a communication log generated by malware. The log analysis unit analyzes the communication log acquired by the log acquisition unit on the basis of predetermined analysis rule and tuning condition. The first analysis unit analyzes an analysis result by the log analysis unit and calculates a recommended tuning value used in an adjustment of the predetermined analysis rule and satisfying the tuning condition.
摘要:
A generation apparatus (10) aggregates a plurality of traffic data for every predetermined target. Further, the generation apparatus (10) samples target traffic data where the number of aggregated traffic data exceeds a threshold. Further, the generation apparatus (10) generates a feature vector representing a feature of the aggregated traffic data for the target that is not sampled, and generates a feature vector representing the feature of the sampled traffic data for the target in which the sampling is performed.