Threat classification in a streaming system
Techniques for identify data usable for generating security recommendations are discussed herein. A system can determine unique identifiers for events associated with a data stream, and determine a frequency of different events occurring in the data stream. The system can generate recommendation data usable for defending the data stream from future malicious events based on a number of similar events occurring over a time period.
1 . A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving detection data comprising a) event information in a data stream associated with a computing device, and b) metadata associated with an event;
determining an identifier for the event based at least in part on applying a function to the detection data;
receiving a set of identifiers associated with a set of events from a previous time;
determining a value indicating similarity between the identifier and each identifier in the set of identifiers; and
configuring recommendation data for the computing device based at least in part on the value, the recommendation data including information indicating a portion of the data stream to protect from a future malicious event.
2 . The system of claim 1 , wherein determining the identifier comprises applying a hash function to the detection data to output a hash value that identifies the event relative to another event.
3 . The system of claim 1 , the operations further comprising:
comparing the value to a similarity threshold; and
transmitting the recommendation data to the computing device based at least in part on the comparing.
4 . The system of claim 1 , the identifier represents a first hash value and the set of identifiers represents a second hash value and a third hash value, and the operations further comprising:
comparing the first hash value with the second hash value and the third hash value; and
determining, based at least in part on the comparing, first similarity between the first hash value and the second hash value and second similarity between the first hash value and the third hash value;
wherein determining the value is based at least in part on the first similarity and the second similarity.
5 . The system of claim 4 , the operations further comprising:
determining that the first similarity or the second similarity meets or exceeds a similarity threshold;
wherein determining the value is further based at least in part on the first similarity or the second similarity meeting or exceeding the similarity threshold.
6 . The system of claim 1 , wherein:
the detection data identifies a malicious process or thread in the event,
the identifier represents a set of concatenated attributes,
the value indicates a number of times the identifier is included in the set of identifiers, and
the metadata comprises one or more of: an operating system identifier of the computing device, a type of object changed, an operation type, an object path, a filesystem path, a registry path, a new object path, a process name, a creation time of the event, or a user identifier.
7 . One or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:
receiving first data comprising a) event information in a data stream associated with a computing device, and b) metadata associated with an event;
determining an identifier for the event based at least in part on applying a function to the first data;
receiving a set of identifiers associated with a set of events from a previous time;
determining a value indicating similarity between the identifier and each identifier in the set of identifiers; and
configuring second data for the computing device based at least in part on the value, the second data including information indicating a portion of the data stream to protect from a future malicious event.
8 . The one or more non-transitory computer-readable media of claim 7 , wherein determining the identifier comprises applying a hash function to the first data to output a hash value that identifies the event relative to another event.
9 . The one or more non-transitory computer-readable media of claim 7 , the operations further comprising:
performing File Integrity Monitoring to monitor an entity for a malicious event; and
determining the first data based at least in part on a result of performing the File Integrity Monitoring.
10 . The one or more non-transitory computer-readable media of claim 7 , the identifier represents a first hash value and the set of identifiers represents a second hash value and a third hash value, and the operations further comprising:
comparing the first hash value with the second hash value and the third hash value; and
determining, based at least in part on the comparing, first similarity between the first hash value and the second hash value and second similarity between the first hash value and the third hash value;
wherein determining the value is based at least in part on the first similarity and the second similarity.
11 . The one or more non-transitory computer-readable media of claim 10 , the operations further comprising:
determining that the first similarity or the second similarity meets or exceeds a similarity threshold;
wherein determining the value is further based at least in part on the first similarity or the second similarity meeting or exceeding the similarity threshold.
12 . The one or more non-transitory computer-readable media of claim 7 , wherein:
the first data identifies a malicious process or thread in the event,
the identifier represents a set of concatenated attributes,
the value indicates a number of times the identifier is included in the set of identifiers, and
the metadata comprises one or more of: an operating system identifier of the computing device, a type of object changed, an operation type, an object path, a filesystem path, a registry path, a new object path, a process name, a creation time of the event, or a user identifier.
13 . The one or more non-transitory computer-readable media of claim 7 , the operations further comprising:
comparing a first attribute of the identifier with multiple attributes associated with the set of identifiers; and
determining, based at least in part on the comparing, similarity between the identifier and one or more identifiers in the set of identifiers;
wherein determining the value is based at least in part on the similarity.
14 . The one or more non-transitory computer-readable media of claim 7 , the operations further comprising:
determining a number of previous identifiers similar to the identifier within a threshold value,
wherein configuring the second data is based at least in part on the number of previous identifiers similar to the identifier within the threshold value.
15 . The one or more non-transitory computer-readable media of claim 7 , the operations further comprising:
determining a first weight for a first attribute of the first data and a second weight for a second attribute;
wherein determining the identifier for the event is further based at least in part on applying the function to the first weight for the first attribute and the second weight for the second attribute.
16 . The one or more non-transitory computer-readable media of claim 7 , the operations further comprising:
receiving a message from the computing device requesting recommendation data for protecting the data stream from the future malicious event; and
accessing, based at least in part on receiving the message, a profile associated with the computing device from a database,
wherein configuring the second data is based at least in part on accessing the profile.
17 . A computer-implemented method comprising:
receiving first data comprising a) event information in a data stream associated with a computing device, and b) metadata associated with an event;
determining an identifier for the event based at least in part on applying a function to the first data;
receiving a set of identifiers associated with a set of events from a previous time;
determining a value indicating similarity between the identifier and each identifier in the set of identifiers; and
configuring second data for the computing device based at least in part on the value, the second data including information indicating a portion of the data stream to protect from a future malicious event.
18 . The computer-implemented method of claim 17 , wherein determining the identifier comprises applying a hash function to the first data to output a hash value that identifies the event relative to another event.
19 . The computer-implemented method of claim 17 , further comprising:
comparing the value to a similarity threshold; and
transmitting the second data to the computing device based at least in part on the comparing.
20 . The computer-implemented method of claim 17 , wherein the identifier represents a first hash value and the set of identifiers represents a second hash value and a third hash value, and further comprising:
comparing the first hash value with the second hash value and the third hash value; and
determining, based at least in part on the comparing, first similarity between the first hash value and the second hash value and second similarity between the first hash value and the third hash value;
wherein determining the value is based at least in part on the first similarity and the second similarity.