Bit-level data extraction and threat detection
Techniques and architectures include representing data with one or more n-dimensional representations and using one or more analysis models to identify target properties associated with the one or more n-dimensional representations. For example, data can be represented as a plurality of points in a coordinate system. A set of points in the plurality of points can be identified and an n-dimensional model can be generated for the set of points. The n-dimensional model can be compared to a plurality of n-dimensional models that are tagged as including a target property associated with malicious behavior, benign behavior, and/or a vulnerability. Based on the comparison, a likelihood can be determined that the data includes the target property.
1. A system comprising:
control circuitry; and
memory communicatively coupled to the control circuitry and storing executable instructions that, when executed by the control circuitry, cause the control circuitry to perform operations comprising:
receiving network traffic data that includes a plurality of bits, the network traffic data being structured in a first format;
extracting a first set of bits from the plurality of bits;
determining a first coordinate for a first point based on the first set of bits;
extracting a second set of bits from the plurality of bits;
determining a second coordinate for the first point based on the second set of bits;
extracting a third set of bits from the plurality of bits;
determining a first coordinate for a second point based on the third set of bits;
extracting a fourth set of bits from the plurality of bits;
determining a second coordinate for the second point based on the fourth set of bits;
mapping the first point and the second point to an n-dimensional space;
using a pattern recognition algorithm to identify a set of points represented in the n-dimensional space;
generating an n-dimensional model for the set of points and storing n-dimension data for the n-dimensional model in a data structure;
processing the n-dimensional model with an Artificial Intelligence (AI) model that is configured to detect data security issues;
based on the processing, determining that the network traffic data includes a data security issue;
removing a portion of the network traffic data that is associated with the data security issue from the network traffic data; and
sending the network traffic data to a device.
2. The system of claim 1 , wherein the processing is based on at least one of a shape of the n-dimensional model, a size of the n-dimensional model, a volume of the n-dimensional model, an area of the n-dimensional model, a number of surfaces of the n-dimensional model, a location of the n-dimensional model within the n-dimensional space, a position of the n-dimensional model relative to another n-dimensional model within the n-dimensional space, or a number of n-dimensional models within the n-dimensional space.
3. The system of claim 1 , wherein the operations further comprise:
determining at least one of a type of the data security issue based on at least one of a shape of the n-dimensional model, a size of the n-dimensional model, a volume of the n-dimensional model, an area of the n-dimensional model, a number of surfaces of the n-dimensional model, a location of the n-dimensional model within the n-dimensional space, a position of the n-dimensional model relative to another n-dimensional model within the n-dimensional space, or a number of n-dimensional models within the n-dimensional space that are associated with the data security issue.
4. The system of claim 1 , wherein the second set of bits are separated from the first set of bits by a particular number of bits.
5. The system of claim 1 , wherein the third set of bits are separated from the second set of bits by a particular number of bits.
6. The system of claim 1 , wherein the first and second sets of bits are located within a beginning portion of the network traffic data and the third and fourth sets of bits are located within an end portion of the network traffic data.
7. The system of claim 1 , wherein the first, second, third, and fourth sets of bits each comprise a same number of bits.
8. A method comprising:
receiving, by control circuitry, network traffic data that includes a plurality of bits, the network traffic data being structured in a first format;
extracting, by the control circuitry, a first set of bits from the plurality of bits;
determining a set of coordinates for a first point based on the first set of bits;
extracting, by the control circuitry, a second set of bits from the plurality of bits;
determining a set of coordinates for a second point based on the second set of bits;
mapping, by the control circuitry, the first point and the second point to an n-dimensional space;
generating an n-dimensional model based on the first point and the second point;
processing the n-dimensional model with an Artificial Intelligence (AI) model that is configured to detect data security issues;
based on the processing, determining that the network traffic data includes a data security issue; and
removing a portion of the network traffic data that is associated with the data security issue from the network traffic data.
9. The method of claim 8 , wherein the second set of bits are separated from the first set of bits by a particular number of bits within the plurality of bits.
10. The method of claim 8 , wherein the first set of bits are located within a beginning portion of the network traffic data and the second set of bits are located within an end portion of the network traffic data.
11. The method of claim 8 , wherein the first and second sets of bits each comprise a same number of bits.
12. The method of claim 8 , further comprising:
generating a first confidence value from the processing, the first confidence value indicating a first likelihood that the network traffic data includes the data security issue;
processing the n-dimensional model with another AI model;
generating a second confidence value indicating a second likelihood that the network traffic data includes the data security issue; and
determining a composite confidence value for the network traffic data based on the first confidence value and the second confidence value;
wherein determining that the network traffic data includes the data security issue is based on the composite confidence value.
13. The method of claim 12 , wherein the first likelihood indicates a likelihood that the network traffic data includes malware.
14. A network device comprising:
one or more network interfaces configured to receive, via a network connection, network traffic data that includes a plurality of bits;
memory storing executable instructions; and
control circuitry communicatively coupled to the memory and configured to execute the executable instructions to:
extract a first set of bits from the plurality of bits;
determine a set of coordinates for a first point based on the first set of bits;
extract a second set of bits from the plurality of bits;
determine a set of coordinates for a second point based on the second set of bits;
map the first point and the second point to an n-dimensional space;
generate an n-dimensional model based on the first point and the second point;
process the n-dimensional model with an Artificial Intelligence (AI) model that is configured to detect data security issues;
based on the processing, determine that the network traffic data includes a data security issue; and
remove a portion of the network traffic data that is associated with the data security issue from the network traffic data.
15. The network device of claim 14 , wherein the second set of bits are separated from the first set of bits by a particular number of bits within the plurality of bits.
16. The network device of claim 14 , wherein the first set of bits are located within a beginning portion of the network traffic data and the second set of bits are located within an end portion of the network traffic data.
17. The network device of claim 14 , wherein the first and second sets of bits each comprise a same number of bits.
18. The network device of claim 14 , wherein the control circuitry is further configured to:
generate a first confidence value from the processing, the first confidence value indicating a first likelihood that the network traffic data includes the data security issue;
process the n-dimensional model with another AI model;
generate a second confidence value indicating a second likelihood that the network traffic data includes the data security issue; and
determine a composite confidence value for the network traffic data based on the first confidence value and the second confidence value;
wherein the control circuitry is configured to determine that the network traffic data includes the data security issue is based on the composite confidence value.
19. The network device of claim 18 , wherein the first likelihood indicates a likelihood that the network traffic data includes malware.
20. The network device of claim 18 , wherein the control circuitry is configured to determine that the network traffic data includes the data security issue by comparing the composite confidence value to a threshold.