Computer-implemented method, computer program product, and computer system for analyzing network connections (identifying network traffic rules)

Abstract

To provide a computer implemented method for analyzing network connections.SOLUTION: The method includes identifying a connection of interest and a corresponding set of connection data. The method additionally includes generating one or more saliency maps corresponding to the connection of interest. The method additionally includes mapping the generated one or more saliency maps to underlying protocols and fields, and identifying one or more values corresponding to each of the underlying protocols and fields. The method additionally includes extracting general correspondences from the identified one or more values corresponding to each of the underlying protocols and fields.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates generally to the field of network analysis, and more particularly to detecting ground rules in a network. [Background technology]

[0002] Deep learning offers a high-performance solution for asset inventory, asset monitoring, and other network traffic analysis. Enterprise asset management involves several important tasks, including asset inventory, asset lifecycle management, and asset monitoring. Deep models offer much higher performance capabilities for metrics such as precision, recall, and F1 score.

[0003] A saliency map is an image processing technique used to distinguish visual features within an image. For example, a full-color image may be converted to a black-and-white image to analyze and describe the most intense colors present in the image. Other examples may include detecting and describing light sources using night vision techniques, using green to describe brightness and black to describe dark areas. The concept of a saliency map is described herein as extending to applications beyond image analysis and is based on features that can describe data other than strictly image data. Summary of the Invention [Problem to be solved by the invention]

[0004] The present invention aims to provide a computer-implemented method and the like that has higher performance capabilities in analyzing network connections, such as asset inventory, asset monitoring, and other network traffic analysis. [Means for solving the problem]

[0005] As disclosed herein, a computer-implemented method for analyzing network connections includes identifying a connection of interest and a corresponding set of connection data. The method further includes generating one or more saliency maps corresponding to the connection of interest. The method further includes mapping the generated one or more saliency maps to underlying protocols and fields and identifying one or more values ​​corresponding to each of the underlying protocols and fields. The method further includes extracting a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields. A computer program product and a computer system corresponding to this method are also disclosed. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a block diagram illustrating a network traffic analysis system in accordance with at least one embodiment of the present invention. [Figure 2] 1 is a flow diagram illustrating a method for analyzing network traffic in accordance with at least one embodiment of the present invention. [Figure 3] FIG. 1 illustrates an exemplary byte stream mapping in accordance with at least one embodiment of the present invention. [Figure 4] FIG. 1 is a block diagram of components of a computing system implementing an image analysis system according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0007] When discussing deep learning, a saliency map corresponds to a visualization technique used to compute an image. This technique derives from the concept of image saliency, which in the context of visual processing refers to the unique features of an image, such as pixels and resolution. These unique features uniquely indicate locations of interest within the image, and a saliency map is a topographical representation of these locations relative to the image. Specifically, a saliency map represents the saliency, or saliency, of all locations within the visual field as a scalar quantity, ultimately guiding the selection of unique locations based on the spatial distribution of saliency.

[0008] 1 is a block diagram illustrating a network traffic analysis system 100 in accordance with at least one embodiment of the present invention. As shown, network traffic analysis system 100 includes computing system 110, network 120, and computing system 130. Network traffic analysis system 100 can enable analysis and identification of rules and dependencies regarding connections within the system.

[0009] Computing system 110 can be a desktop computer, a laptop computer, a specialized computer server, or any other computer system known in the art. In some embodiments, computing system 110 is a computer system utilizing clustered computers to act as a single pool of seamless resources. Generally, computing system 110 represents any electronic device or combination of electronic devices capable of receiving and transmitting data, as described in more detail with respect to FIG. 4. Computing system 110 can include internal and external hardware components, as shown and described in more detail with respect to FIG. 4.

[0010] As shown, computing system 110 includes connection analysis application 115. Connection analysis application 115 may be configured to perform a network traffic analysis method, such as that described with respect to FIG. 2. Connection analysis application 115 may be capable of performing any of the operational steps detailed above or below. In at least some embodiments, connection analysis application 115 is configured to analyze a connection between computing system 110 and any of computing systems 130A and 130B.

[0011] Each computing system 130 can be a desktop computer, a laptop computer, a specialized computer server, or any other computing system known in the art. In some embodiments, computing system 130 is a computing system utilizing clustered computers to act as a single pool of seamless resources. Generally, computing system 130 represents any electronic device or combination of electronic devices capable of receiving and transmitting data, as described in more detail with respect to FIG. 4. Computing system 130 can include internal and external hardware components, as shown and described in more detail with respect to FIG. 4.

[0012] Network 120 may be, for example, a local area network (LAN), a wide area network (WAN) such as the Internet, or a combination of the two, and may include wired, wireless, or fiber optic connections. In general, network 120 may be any combination of connections and protocols that support communication between computing system 110 and computing system 130.

[0013] 2 is a flow diagram illustrating a method 200 for analyzing network traffic in accordance with at least one embodiment of the present invention. As shown, the method 200 includes identifying connections of interest (210), generating a saliency map corresponding to the connections of interest (220), mapping the generated saliency map to underlying protocols and fields (230), identifying one or more values ​​corresponding to each of the underlying protocols and fields (240), extracting general correspondences from the identified one or more values ​​corresponding to each of the underlying protocols and fields (250), and generating general rules representing the extracted correspondences (260).

[0014] Identifying 210 a network or connection of interest can include receiving an indication of one or a set of connections to analyze. In at least some embodiments, identifying 210 a connection of interest includes identifying a set of network traffic data. The network traffic data can include one or more byte streams. In at least some embodiments, identifying 210 a connection of interest includes identifying one or more well-defined protocols over which data is respectively transmitted to the connection of interest.

[0015] Generating 220 a saliency map corresponding to the connection of interest can include performing attention-based modeling on data corresponding to the connection of interest. In at least some embodiments, generating 220 a saliency map corresponding to the connection of interest includes applying an attention-based model to one or more byte streams corresponding to the connection of interest. The attention-based model can be configured to attribute attention weights to various portions of the byte stream. In at least some embodiments, the attention weights are applied to accurately reflect the importance of the analyzed portion of the byte stream. Attention models can divide attention into two types: global attention and local attention. When global attention is performed, attention is paid to all source positions within the byte stream, while when local attention is performed, attention is paid to only some source positions within the byte stream. With local attention, the positions to which attention is paid correspond to positions that are most likely to contain salient bytes. With global attention, it may be impossible or inaccurate to pay attention to specific bytes, and therefore attention may be paid uniformly across all byte positions. In additional embodiments, local and global attention can refer to the distribution of attention paid to a single byte location. For example, a byte stream can be divided into various larger chunks or segments. For each of these segments, the byte location can hold a unique "importance" or weight. Therefore, in such a situation, local attention can be applied, such that the byte location for a first segment holds a first weight, and the byte at that same location for a second segment holds a second weight.In embodiments where identifying such segments is not applicable, or where identifying various byte positions prior to analyzing the byte stream is not feasible, global attention can be implemented instead to avoid mischaracterizing values ​​within the byte stream. In at least some embodiments, the attention-based model used is trained on the raw TCP / UDP stream. The model's attention weights provide a saliency map by highlighting sequences of bytes that play a significant role in the prediction.

[0016] Generating saliency maps corresponding to the connections of interest (220) can further include creating Gaussian pyramids to create feature maps for one or more features of interest corresponding to the connections of interest. Pyramid representations are a type of multiscale signal representation in which a signal or image undergoes repeated smoothing and subsampling. Pyramid representations can be divided into two main types: low-pass and band-pass. Creating a low-pass pyramid involves smoothing an image or signal and optionally subsampling the smoothed image by a factor of two along each coordinate direction. The resulting image or signal is then subjected to the same procedure, and this cycle is performed repeatedly. Each cycle results in a smaller image or signal, increasing smoothing but decreasing spatial sampling density. When performed on an image, these resulting graphical representations result in a pyramid, with the original image on top and the resulting images stacked on top of each other. Gaussian pyramids are specifically deweighted and therefore reduced using a Gaussian mean. Each pixel or byte that contains the local mean corresponds to a neighboring pixel or byte at a lower level in the pyramid.

[0017] In some embodiments, generating 220 a saliency map corresponding to a connection of interest includes aggregating one or more generated saliency maps for a class to form a rule for that class. To illustrate this point, one may wish to look at all connections from devices from a particular vendor. By aggregating results across multiple connections, it may become apparent that having a value of V in field k may be highly specific to that particular vendor. For each input, a sliding window sums the attention weights for that sequence. Weights for each sequence are then calculated and summed across multiple instances, each of which may correspond to a distinct connection. The goal of this window is to learn important sequences. Continuing with the example above, it may become apparent that the sequence "ABCD" in field k may be highly specific to another vendor. In embodiments of the present invention, a byte-valued saliency map is constructed; in other words, for a byte stream, each byte has a value, and the saliency method assigns each byte a relevance score. It should be understood that the significance of a value relative to a byte is entirely dependent on the context of the byte stream, and therefore it is impractical to attempt to generalize which values ​​may and may not be evaluated as significant. Byte values ​​may be assigned a relevance score before the byte stream is received, taking into account their perceived significance relative to the context of the byte stream in which they are received.

[0018] Mapping 230 the generated saliency map to underlying protocols and fields can include forging an association between a portion of the byte stream received for a given connection and the underlying protocol indicated by that portion of the byte stream. For example, for a TCP connection, bytes X through (X+K) for positions X and X+K can be highlighted by the saliency map. When it is determined based on the results of the saliency map that these bytes or portions are of particular interest, mapping 230 the generated saliency map to underlying protocols continues by identifying the positions of the bytes and determining whether the positions correspond to a particular field. Referring to the TCP connection example discussed above, analyzing bytes X through X+K for a TCP connection can result in the bytes corresponding to the corresponding HTTP protocol user agent field. In this case, mapping 230 the generated saliency map to underlying protocols and fields can include associating the portion of the saliency map (i.e., the portion corresponding to bytes X through X+K) with the user agent field that it affects.

[0019] FIG. 3 illustrates an example of a process for mapping sections of a byte stream to underlying protocol structures and fields. As illustrated, the byte stream is divided into sections, as indicated by the grayscale. Each of these sections is identified as corresponding to one or more fields in the illustrated protocol structure. As illustrated, various sections of the byte stream correspond to multiple protocol structure types. These correspondences are indicated by lines connecting each section of the byte stream to one or more fields in one or more of the underlying protocol structures. It should be understood that FIG. 3 corresponds to only a single example of a mapping from a saliency map (or byte stream) to underlying fields and protocols. Many embodiments may exist.

[0020] Identifying one or more values ​​corresponding to each of the underlying protocols and fields (240) can include identifying at least one value corresponding to each of the identified fields for the association between the generated saliency map and the connection of interest.

[0021] Extracting 250 a general correspondence from the identified one or more values ​​corresponding to each of the lower-layer protocols and fields can include identifying one or more entities or features indicated by the identified one or more values ​​corresponding to each of the lower-layer protocols and fields. For example, in some cases, a value for a particular field can indicate a network address indicating an entity or device that can provide or receive data corresponding to the appropriate field or lower-layer protocol. In other words, the identified one or more values ​​can indicate one or more entities, devices, or addresses that influence or contribute to the portions of the byte stream transmitted in the connection of interest that are most important according to attention modeling. For example, consider a situation in which five portions of a byte stream are identified as being of high importance according to a corresponding attention-based model. These portions may be the portions that receive the most attention, i.e., the portions that are most frequently observed or interacted with. In this embodiment, four of the identified portions of the byte stream correspond to network address X. In other words, these portions of the byte stream, in one way or another, influence or are influenced by the device located at network address X. In such a case, data provided by or to a device corresponding to network address X may be considered highly sensitive.

[0022] In additional embodiments, extracting 250 a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields further includes determining whether the identified one or more values ​​share a relationship to one another. For example, two portions of a byte stream may correspond to requests or commands that depend on one another. A simple exemplary embodiment is one in which an initially identified portion of the byte stream provides some data X, and a later portion of the byte stream utilizes some portion of data X. Such portions may be tagged or labeled as corresponding to or depending on one another.

[0023] Generating 260 a general rule representing the extracted correspondence can include determining whether a trend exists between an identified portion of the byte stream and a value identified for the identified portion and the correspondence. For example, generating 260 a general rule representing the extracted correspondence can include determining that each portion of the byte stream exhibiting a value of X is identified as significant. A corresponding rule can then be generated so that as soon as a portion of the byte stream is determined to correspond to the value X, the portion can be immediately marked as significant, prior to any additional analysis. For example, if a byte stream has a particular value V at position k, it can be determined that the corresponding device has established a connection to server X. Identifying such correspondence can similarly enable the creation of subsequent rules based on hypotheses that can be made in light of the correspondence. In other embodiments, generating 260 a general rule representing the extracted correspondence can include determining whether all instances of a value correspond to data received from a particular location; in such embodiments, this rule can indicate that any byte stream portion having a value X in a particular field corresponds to data provided by a particular device. Generating such rules can eliminate the need for pre-analysis of subsequent connections, thereby eliminating the need for additional processing.

[0024] 4 illustrates a block diagram of components of a computing system 110 in accordance with an illustrative embodiment of the invention. It should be understood that FIG. 4 is only intended to provide a description of one implementation and is not intended to imply any limitation with respect to the environments in which different embodiments may be implemented. Many modifications to the depicted environment may be made.

[0025] As shown, computer 400 includes a communications fabric 402 that provides communication between a computer processor 404, memory 406, persistent storage 408, a communications unit 412, and an input / output (I / O) interface 414. Communications fabric 402 may be implemented by any architecture designed to pass data and / or control information between processors (e.g., microprocessors, communications and network processors), system memory, peripheral devices, and any other hardware components in a system. For example, communications fabric 402 may be implemented by one or more buses.

[0026] Memory 406 and persistent storage 408 are computer-readable storage media. In this embodiment, memory 406 includes random access memory (RAM) 416 and cache memory 418. In general, memory 406 may include any suitable volatile or non-volatile computer-readable storage media.

[0027] One or more programs may be stored in persistent storage 408 for access and / or execution by one or more of the respective computer processors 404 via one or more memories in memory 406. In this embodiment, persistent storage 408 includes a magnetic hard disk drive. Alternatively or in addition to a magnetic hard disk drive, persistent storage 408 may include a solid-state hard drive, a semiconductor storage device, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, or any other computer-readable storage medium capable of storing program instructions or digital information.

[0028] The media used by persistent storage 408 may also be removable. For example, a removable hard drive may be used for persistent storage 408. Other examples include optical and magnetic disks, thumb drives, and smart cards that are inserted into a drive for transfer to another computer-readable storage medium that is also part of persistent storage 408.

[0029] In these examples, communications unit 412 provides for communications with other data processing systems or devices. In these examples, communications unit 412 includes one or more network interface cards. Communications unit 412 may provide communications through the use of either or both physical and wireless communications links.

[0030] The I / O interface 414 allows for the input and output of data with other devices that may be connected to the computer 400. For example, the I / O interface 414 may provide a connection to external devices 420, such as a keyboard, keypad, touch screen, or any other suitable input device, or a combination thereof. The external devices 420 may also include portable computer-readable storage media, such as thumb drives, portable optical or magnetic disks, and memory cards. Software and data used to implement embodiments of the present invention may be stored on such portable computer-readable storage media and loaded into persistent storage 408 via the I / O interface 414. The I / O interface 414 also connects to a display 422.

[0031] Display 422 provides a mechanism for displaying data to a user and may be, for example, a computer monitor.

[0032] The programs described herein are identified based on the application in which they are implemented in specific embodiments of the invention, but it should be understood that any specific program terminology is used herein for convenience only and therefore should not limit the invention to use with only any specific application identified and / or suggested by such terminology.

[0033] The present invention may be a system, method, or computer program product, or combination thereof, at any possible level of technical detail integration. The computer program product may include a computer-readable storage medium having computer-readable program instructions for causing a processor to implement aspects of the present invention.

[0034] A computer-readable storage medium may be a tangible device capable of retaining and storing instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. A non-exhaustive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical coding devices such as punch cards or groove-in-the-loop structures having instructions recorded thereon, and any suitable combination of the above. As used herein, computer-readable storage media should not be construed as ephemeral signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through fiber optic cable), or electrical signals transmitted through wires.

[0035] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or can be downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, or a wireless network, or a combination thereof. The network can include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface within each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage on a computer-readable storage medium within the respective computing / processing device.

[0036] The computer-readable program instructions for carrying out the operations of the present invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for an integrated circuit, or source or object code, written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, C++, and procedural programming languages ​​such as the “C” programming language, or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may form a connection to an external computer (e.g., via the Internet using an Internet Service Provider). In some embodiments, electronic circuitry, including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may execute computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry to perform aspects of the present invention.

[0037] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0038] These computer-readable program instructions can be provided to a processor of a computer or other programmable data processing apparatus to produce a machine, such that the instructions, when executed by the processor of the computer or other programmable data processing apparatus, generate means for performing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer-readable program instructions can also be stored in a computer-readable storage medium, such that the computer-readable storage medium on which the instructions are stored comprises an article of manufacture containing instructions that implement aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams, and can direct a computer, programmable data processing apparatus, or other device, or combination thereof, to function in a particular manner.

[0039] The computer-readable program instructions may also be loaded into a computer, other programmable data processing apparatus, or other device to cause the computer, other programmable apparatus, or other device to perform a series of operational steps to create a computer-implemented process, such that the instructions, which execute on the computer, other programmable apparatus, or other device, perform the functions / operations specified in one or more blocks of the flowcharts and / or block diagrams.

[0040] The flowcharts and block diagrams in these figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions, including one or more executable instructions for implementing a specified logical function(s). In some alternative implementations, the functions described in the blocks may occur out of the order shown in the figures. For example, depending on the functionality required, two blocks shown in succession may actually be implemented as a single step, may be executed concurrently, substantially concurrently, with partial or complete overlap in time, or the blocks may possibly be executed in reverse order. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or operations or implements a combination of dedicated hardware and computer instructions.

[0041] The description of various embodiments of the present invention is provided for illustrative purposes and is not intended to be exhaustive or limiting with respect to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the invention. The terminology used herein has been selected to best explain the principles of the embodiments, practical applications, or technical improvements over commercially available technology, or to enable those skilled in the art to understand the embodiments disclosed herein. [Explanation of symbols]

[0042] 100 Network Traffic Analysis Systems 110 Computing Systems 115 Connection Analysis Applications 120 Network 130A Computing System 130B Computing Systems 400 computers 402 Communication Fabric 404 Computer Processor 406 memory 408 Persistent Storage 412 Communication Unit 414 Input / Output (I / O) Interface 416 Random Access Memory (RAM) 418 Cache Memory 420 External Devices 422 Display

Claims

1. 1. A computer-implemented method for analyzing network connectivity, comprising: identifying a connection of interest and a corresponding set of connection data; generating one or more saliency maps corresponding to the target connection, the maps including creating maps indicating attention devoted to portions of data transmitted over the target connection; mapping the generated one or more saliency maps to underlying protocols and fields; identifying one or more values ​​corresponding to each of the underlying protocols and fields; and extracting a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields.

2. The computer-implemented method of claim 1 , further comprising generating general rules that represent the extracted correspondences.

3. 2. The computer-implemented method of claim 1, wherein the corresponding set of connection data comprises one or more byte streams.

4. 1. A computer-implemented method for analyzing network connectivity, comprising: identifying a connection of interest and a corresponding set of connection data; generating one or more saliency maps corresponding to the connections of interest; mapping the generated one or more saliency maps to underlying protocols and fields; identifying one or more values ​​corresponding to each of the underlying protocols and fields; extracting a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields; the corresponding set of connection data includes one or more byte streams; A computer-implemented method, wherein generating one or more saliency maps corresponding to the target connection includes generating one or more saliency maps corresponding to the one or more byte streams such that portions of the byte streams are emphasized according to attention paid to the portions of the byte streams.

5. 5. The computer-implemented method of claim 4, wherein mapping the generated one or more saliency maps to lower layer protocols and fields comprises mapping one or more portions of the byte stream to lower layer fields or protocols affected by the one or more portions of the byte stream.

6. generating a saliency map corresponding to the connection of interest; identifying a context corresponding to the one or more received byte streams; analyzing the byte stream to determine an importance level corresponding to one or more values ​​in the byte stream with respect to the identified context; and assigning one or more weights to the values ​​in the byte stream based on the determined level of importance.

7. 1. A computer program for analyzing network connections, comprising: one or more computer-readable storage media; and program instructions stored on the one or more computer-readable storage media, the program instructions comprising: Identify the connection you are interested in, generating a saliency map corresponding to said target connection; Mapping the generated saliency map to underlying protocols and fields; identifying one or more values ​​corresponding to each of the underlying protocols and fields; instructions for extracting a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields; 1. A computer program product, comprising: instructions for generating one or more saliency maps corresponding to the target connection, the instructions for creating a map indicating attention given to portions of data transmitted over the target connection.

8. The computer program product of claim 7 , further comprising instructions for generating general rules that represent the extracted correspondences.

9. 8. The computer program product of claim 7, wherein the corresponding set of connection data comprises one or more byte streams.

10. 1. A computer program for analyzing network connections, comprising: one or more computer-readable storage media; and program instructions stored on the one or more computer-readable storage media, the program instructions comprising: Identify the connection you are interested in, generating a saliency map corresponding to said target connection; Mapping the generated saliency map to underlying protocols and fields; identifying one or more values ​​corresponding to each of the underlying protocols and fields; instructions for extracting a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields; the corresponding set of connection data includes one or more byte streams; a computer program product, the computer program product comprising: instructions for generating one or more saliency maps corresponding to the target connection, the instructions for generating one or more saliency maps corresponding to the one or more byte streams such that portions of the byte streams are emphasized according to attention paid to the portions of the byte streams.

11. 11. The computer program product of claim 10, wherein the instructions for mapping the generated one or more saliency maps to lower layer protocols and fields comprise instructions for mapping one or more portions of the byte stream to lower layer fields or protocols affected by the one or more portions of the byte stream.

12. instructions for generating a saliency map corresponding to the target connection, identifying a context corresponding to the one or more received byte streams; analyzing the byte stream to determine an importance level corresponding to one or more values ​​in the byte stream with respect to the identified context; 10. The computer program product of claim 9, comprising instructions for assigning one or more weights to the values ​​in the byte stream based on the determined level of importance.

13. 1. A computer system for analyzing network connections, comprising: one or more computer processors; one or more computer-readable storage media; and program instructions stored on the computer-readable storage medium for execution by at least one of the one or more computer processors, the program instructions comprising: Identify the connection you are interested in, generating a saliency map corresponding to said target connection; Mapping the generated saliency map to underlying protocols and fields; identifying one or more values ​​corresponding to each of the underlying protocols and fields; instructions for extracting a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields; 10. A computer system, wherein the instructions for generating one or more saliency maps corresponding to the target connection include instructions for creating a map indicating attention given to portions of data transmitted over the target connection.

14. 14. The computer system of claim 13, further comprising instructions for generating general rules that represent the extracted correspondences.

15. 14. The computer system of claim 13, wherein the corresponding set of connection data comprises one or more byte streams.

16. 1. A computer system for analyzing network connections, comprising: one or more computer processors; one or more computer-readable storage media; and program instructions stored on the computer-readable storage medium for execution by at least one of the one or more computer processors, the program instructions comprising: Identify the connection you are interested in, generating a saliency map corresponding to said target connection; Mapping the generated saliency map to underlying protocols and fields; identifying one or more values ​​corresponding to each of the underlying protocols and fields; instructions for extracting a general correspondence from the identified one or more values ​​corresponding to each of the underlying protocols and fields; the corresponding set of connection data includes one or more byte streams; A computer system, wherein the instructions for generating one or more saliency maps corresponding to the target connection include instructions for generating one or more saliency maps corresponding to the one or more byte streams such that portions of the byte streams are emphasized according to attention paid to the portions of the byte streams.

17. 17. The computer system of claim 16, wherein the instructions for mapping the generated one or more saliency maps to lower layer protocols and fields comprise instructions for mapping one or more portions of the byte stream to lower layer fields or protocols affected by the one or more portions of the byte stream.

Images