Cluster-based precision mitigation of network attacks
Provided are methods and systems for cluster-based mitigation of a network attack. A method for cluster-based mitigation of a network attack may commence with detecting an unusual pattern in network data traffic associated with data sources. The method may further include extracting signature parameters associated with the network data traffic. The signature parameters may be indicative of the network attack. The method may continue with assigning importance weights to the signature parameters based on historical signature data to generate weighted signature parameters. The method may further include building a decision tree for the data sources based on the weighted signature parameters. The method may continue with creating an optimal number of clusters for the data sources based on an analysis of the decision tree. The method may further include selectively taking at least one mitigating action with regard to the data sources within the clusters.
1. A system for cluster-based mitigation of a network attack, the system comprising:
at least one processor configured to:
detect an unusual pattern in network data traffic associated with data sources;
extract signature parameters associated with the network data traffic, the signature parameters being indicative of the network attack;
assign importance weights to the signature parameters based on historical signature data to generate weighted signature parameters, each of the weighted signature parameters being associated with one of the data sources;
build a decision tree for the data sources based on the weighted signature parameters;
group the weighted signature parameters into an optimal number of clusters based on an analysis of the decision tree; and
for each of the clusters, selectively take at least one attack mitigating action with regard to one or more of the data sources associated with the weighted signature parameters grouped within each of the clusters; and
a storage unit in communication with the at least one processor, the storage unit being configured to store at least the historical signature data.
2. The system of claim 1 , wherein the optimal number of clusters is predetermined based on historical information associated with the decision tree.
3. The system of claim 1 , wherein the optimal number of clusters is determined using a K-Means algorithm using silhouette analysis with varying values of K.
4. The system of claim 1 , wherein the at least one processor is further configured to determine radiuses for each cluster, the at least one mitigating action being taken with regard to the data sources inside the radiuses.
5. The system of claim 4 , wherein the radiuses are determined using at least one machine learning technique.
6. The system of claim 1 , wherein the at least one processor is further configured to accelerate the extracting of the signature parameters by discarding low volume signature parameters.
7. The system of claim 1 , wherein the at least one processor is further configured to implement filtering based on historical data until an analysis of the clusters is complete.
8. The system of claim 1 , wherein the signature parameters include components associated with a plurality of data layers packets.
9. The system of claim 1 , wherein the at least one mitigating action includes filtering the network data traffic to block traffic coming from the data sources classified as undesired.
10. The system of claim 1 , wherein the signature parameters include at least one of the following: a repeating source port, an IP packet length, and a packet fragmentation.
11. The system of claim 1 , wherein the signature parameters of the clusters are analyzed using at least one machine learning technique.
12. A method for cluster-based mitigation of a network attack, the method comprising:
detecting an unusual pattern in network data traffic associated with data sources;
extracting signature parameters associated with the network data traffic, the signature parameters being indicative of the network attack;
assigning importance weights to the signature parameters based on historical signature data to generate weighted signature parameters, each of the weighted signature parameters being associated with one of the data sources;
building a decision tree for the data sources based on the weighted signature parameters;
grouping the weighted signature parameters into an optimal number of clusters based on an analysis of the decision tree; and
for each of the clusters, selectively taking at least one attack mitigating action with regard to one or more of the data sources associated with the weighted signature parameters grouped within each of the clusters.
13. The method of claim 12 , wherein the optimal number of clusters is predetermined based on historical information associated with the decision tree.
14. The method of claim 12 , wherein the optimal number of clusters is determined using a K-Means algorithm using silhouette analysis with varying values of K.
15. The method of claim 12 , further comprising determining radiuses for each cluster, the at least one mitigating action being taken with regard to the data sources inside the radiuses.
16. The method of claim 15 , wherein the radiuses are determined using at least one machine learning technique.
17. The method of claim 12 , further comprising accelerating the extracting of the signature parameters by discarding low volume signature parameters.
18. The method of claim 12 , further comprising implementing filtering based on historical data until an analysis of the clusters is complete.
19. The method of claim 12 , wherein the at least one mitigating action includes filtering the network data traffic to block traffic coming from the data sources classified as undesired.
20. A system for cluster-based mitigation of a network attack, the system comprising:
at least one processor configured to:
detect an unusual pattern in network data traffic associated with data sources;
extract signature parameters associated with the network data traffic, the signature parameters being indicative of the network attack;
assign importance weights to the signature parameters based on historical signature data to generate weighted signature parameters, each of the weighted signature parameters being associated with one of the data sources;
build a decision tree for the data sources based on the weighted signature parameters;
group the weighted signature parameters into an optimal number of clusters based on an analysis of the decision tree, wherein the optimal number of clusters is predetermined based on historical information associated with the decision tree;
determine radiuses for each cluster, the at least one mitigating action being taken with regard to the data sources inside the radiuses, wherein the radiuses are determined using at least one machine learning technique; and
for each of the clusters, selectively take at least one attack mitigating action with regard to one or more of the data sources associated with the weighted signature parameters grouped within each of the clusters; and
a storage unit in communication with the at least one processor, the storage unit being configured to store at least the historical signature data and the historical information associated with the decision tree.