Malicious file detection methods, equipment, storage media and devices for the Industrial Internet
By extracting feature data from suspicious file samples, dynamic prediction and propagation behavior monitoring are performed, solving the problem of malicious file detection in the industrial internet and achieving accurate identification of malicious files and improvement of network security.
Patent Information
- Application Number
- CN202310789678.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-29
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2043-06-29
AI Technical Summary
The lack of effective methods in existing technologies to accurately detect malicious files in the Industrial Internet makes it impossible to effectively prevent and control cybersecurity issues.
By extracting feature data from suspicious file samples, dynamic prediction and propagation behavior monitoring are performed. Combining feature data, dynamic prediction results, and behavior monitoring results, malicious files can be detected.
It improves the security of the Industrial Internet, enabling accurate detection and identification of malicious files to prevent them from compromising network security.
Smart Images

Figure CN119232401B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of network security technology, and in particular to a method, device, storage medium and apparatus for detecting malicious files in the industrial internet. Background Technology
[0002] The Industrial Internet is a deep integration of emerging communication technologies with the industrial economy. Its derivatives include new automated infrastructure, application models, and an industrial ecosystem. By connecting all elements of industry—people, machines, things, and methods—it constructs a new industrial service system covering the entire value chain and industrial chain, providing a new path for the digital, automated, intelligent, and networked development and innovation of industry. The Industrial Internet is not simply an application of the Internet in the industrial field, but rather a deep integration of its connotation and extension. It represents a new business model, demonstrating the empowerment, intelligence, and value creation of new industries, and can powerfully promote the rapid improvement, cost reduction, efficiency enhancement, and safe development of my country's real economy.
[0003] With the rapid development of the Industrial Internet, various cybersecurity issues are constantly emerging. Current technologies lack effective prevention and control measures for the Industrial Internet, making it impossible to accurately detect malicious files within it.
[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention
[0005] The main objective of this invention is to provide a method, device, storage medium, and apparatus for detecting malicious files in the industrial internet, aiming to solve the technical problem that existing technologies lack prevention and control measures for the industrial internet and cannot accurately detect malicious files in the industrial internet.
[0006] To achieve the above objectives, the present invention provides a method for detecting malicious files in the industrial internet, the method comprising the following steps: Extracting feature data from suspicious document samples; The dynamics of the suspicious file samples are predicted to obtain dynamic prediction results; The propagation behavior of the suspicious file samples is monitored to obtain the behavior monitoring results; Malicious files are detected based on the feature data, the dynamic prediction results, and the behavior monitoring results.
[0007] Optionally, the step of monitoring the propagation behavior of the suspicious file sample and obtaining the behavior monitoring results includes: Obtain the propagation scenario of the suspicious file sample; Based on the aforementioned propagation scenario, the propagation behavior of the suspicious file sample is monitored to obtain the behavior monitoring results.
[0008] Optionally, the step of monitoring the propagation behavior of the suspicious file sample based on the propagation scenario and obtaining the behavior monitoring results includes: When the propagation scenario is an intranet scenario, the file type, process parameters, and file path of the suspicious file sample are obtained; The propagation behavior of the suspicious file sample is monitored based on the file type, process parameters, and file path to obtain behavior monitoring results.
[0009] Optionally, the step of monitoring the propagation behavior of the suspicious file sample based on the propagation scenario and obtaining the behavior monitoring results includes: When the propagation scenario is an external network scenario, detect whether the feature data contains an anomaly identifier; Based on the detection results, the propagation behavior of the suspicious file samples is monitored to obtain behavioral monitoring results.
[0010] Optionally, before the step of extracting feature data from the suspicious document sample, the method further includes: Suspicious files in the network to be detected are identified using preset probes; By using preset inducement resources to induce the suspicious files to launch a network attack, a sample of the suspicious files is obtained.
[0011] Optionally, the step of identifying suspicious files in the network to be detected using a preset probe includes: Network information of the network to be detected is obtained through a preset probe, and the network information is analyzed. Based on the analysis results, the files were restored to obtain the suspicious files.
[0012] Optionally, the step of inducing the suspicious file to launch a network attack through preset inducement resources to obtain a suspicious file sample includes: Build virtual networks; The suspicious file is induced to launch a cyberattack using the virtual network and preset inducement resources, thereby obtaining a sample of the suspicious file.
[0013] Optionally, the step of dynamically predicting the suspicious file sample to obtain a dynamic prediction result includes: The dynamic prediction of the suspicious file samples is obtained by using a preset bidirectional long short-term memory network model.
[0014] Optionally, the feature data is IPR feature data.
[0015] Optionally, after the step of detecting malicious files based on the feature data, the dynamic prediction result, and the behavior monitoring result, the method further includes: When a malicious file is detected, the malicious file is intercepted; Generate alarm information corresponding to the malicious file.
[0016] Optionally, the step of generating the alarm information corresponding to the malicious file includes: Obtain the source and target addresses of the malicious file; Based on the source address and the target address, generate alarm information corresponding to the malicious file.
[0017] Furthermore, to achieve the above objectives, the present invention also proposes an industrial internet malicious file detection device, which includes a memory, a processor, and an industrial internet malicious file detection program stored on the memory and executable on the processor. The industrial internet malicious file detection program is configured to implement the industrial internet malicious file detection method described above.
[0018] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing an industrial internet malicious file detection program, which, when executed by a processor, implements the industrial internet malicious file detection method as described above.
[0019] In addition, to achieve the above objectives, the present invention also proposes a malicious file detection device for the industrial internet, which includes: a data extraction module, a dynamic prediction module, a behavior monitoring module, and a file detection module. The data extraction module is used to extract feature data from suspicious file samples; The dynamic prediction module is used to dynamically predict the suspicious file sample and obtain dynamic prediction results. The behavior monitoring module is used to monitor the propagation behavior of the suspicious file sample and obtain behavior monitoring results; The file detection module is used to detect malicious files based on the feature data, the dynamic prediction results, and the behavior monitoring results.
[0020] Optionally, the behavior monitoring module is also used to obtain the propagation scenario of the suspicious file sample; The behavior monitoring module is also used to monitor the propagation behavior of the suspicious file sample based on the propagation scenario and obtain behavior monitoring results.
[0021] Optionally, the behavior monitoring module is further configured to obtain the file type, process parameters, and file path of the suspicious file sample when the propagation scenario is an intranet scenario; The behavior monitoring module is also used to monitor the propagation behavior of the suspicious file sample based on the file type, the process parameters, and the file path, and obtain behavior monitoring results.
[0022] Optionally, the behavior monitoring module is further configured to detect whether the feature data contains an abnormal identifier when the propagation scenario is an external network scenario; The behavior monitoring module is also used to monitor the propagation behavior of the suspicious file sample based on the detection results, and obtain behavior monitoring results.
[0023] Optionally, the malicious file detection device for the industrial internet further includes: a sample acquisition module; The sample acquisition module is used to identify suspicious files in the network to be detected using a preset probe; The sample acquisition module is also used to induce the suspicious file to launch a network attack through preset inducing resources, thereby obtaining a suspicious file sample.
[0024] Optionally, the sample acquisition module is further configured to acquire network information of the network to be detected through a preset probe, and analyze the network information; The sample acquisition module is also used to restore files based on the analysis results and obtain suspicious files.
[0025] Optionally, the sample acquisition module is also used to construct a virtual network; The sample acquisition module is also used to induce the suspicious file to launch a network attack through the virtual network and preset inducement resources, thereby obtaining a suspicious file sample.
[0026] This invention discloses a method for extracting feature data from suspicious file samples, predicting the dynamics of suspicious file samples to obtain dynamic prediction results, monitoring the propagation behavior of suspicious file samples to obtain behavior monitoring results, and detecting malicious files based on feature data, dynamic prediction results, and behavior monitoring results. Because this invention can accurately detect malicious files in the industrial internet by extracting features, making dynamic predictions, and monitoring the behavior of suspicious file samples, it improves the security of the industrial internet. Attached Figure Description
[0027] Figure 1 This is a schematic diagram of the structure of a malicious file detection device for the industrial internet in the hardware operating environment involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the first embodiment of the malicious file detection method for the industrial internet of the present invention. Figure 3 This is a flowchart illustrating the second embodiment of the malicious file detection method for the industrial internet of the present invention. Figure 4 This is a flowchart illustrating the third embodiment of the malicious file detection method for the industrial internet of the present invention. Figure 5 This is a structural block diagram of the first embodiment of the malicious file detection device for the industrial internet of the present invention.
[0028] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0029] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0030] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a malicious file detection device for the industrial internet in the hardware operating environment involved in the embodiments of the present invention.
[0031] like Figure 1 As shown, the malicious file detection device for the Industrial Internet may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen, and optionally, it may also include a standard wired interface or a wireless interface. In this invention, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.
[0032] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on malicious file detection devices for the Industrial Internet and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0033] like Figure 1As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a malicious file detection program for the industrial internet.
[0034] exist Figure 1 In the industrial internet malicious file detection device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to user equipment; the industrial internet malicious file detection device calls the industrial internet malicious file detection program stored in the memory 1005 through the processor 1001 and executes the industrial internet malicious file detection method provided in the embodiment of the present invention.
[0035] Based on the above hardware structure, an embodiment of the malicious file detection method for the industrial internet of the present invention is proposed.
[0036] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the malicious file detection method for industrial internet of the present invention, which presents the first embodiment of the malicious file detection method for industrial internet of the present invention.
[0037] In the first embodiment, the malicious file detection method for the Industrial Internet includes the following steps: Step S10: Extract feature data from suspicious document samples.
[0038] It should be understood that the execution subject of the method in this embodiment can be an industrial internet malicious file detection device with data processing, network communication and program running functions, such as a server, or other electronic devices that can achieve the same or similar functions. This embodiment does not limit this.
[0039] It should be noted that suspicious file samples can be pre-set or obtained by the malicious file detection equipment of the Industrial Internet from the network to be detected; this embodiment does not impose any restrictions on this. The network to be detected can be any network that requires malicious file detection within the Industrial Internet, for example, the Industrial Internet itself.
[0040] It is understandable that extracting feature data from suspicious file samples can be based on data identifiers. These data identifiers are used to distinguish different data points.
[0041] Step S20: Predict the dynamics of the suspicious file sample to obtain the dynamic prediction result.
[0042] It should be understood that, in order to determine whether a suspicious file will endanger network security in the future, this embodiment also predicts the dynamics of the suspicious file sample.
[0043] It is understandable that predicting the dynamics of suspicious file samples and obtaining dynamic prediction results can be achieved by using a pre-set prediction model to predict the dynamics of the suspicious file samples. The pre-set prediction model can be pre-configured to predict the file's dynamics; for example, the pre-set prediction model can be a neural network model.
[0044] Step S30: Monitor the propagation behavior of the suspicious file sample and obtain the behavior monitoring results.
[0045] It should be understood that, in order to determine whether the current propagation behavior of a suspicious file endangers network security, this embodiment also monitors the propagation behavior of the suspicious file sample.
[0046] It is understandable that monitoring the spread of suspicious document samples can involve obtaining information about the spread of suspicious document samples and monitoring the spread of suspicious document samples based on that information.
[0047] Step S40: Detect malicious files based on the feature data, the dynamic prediction results, and the behavior monitoring results.
[0048] It should be understood that when the feature data is malicious, or the dynamic prediction result indicates that there will be malicious dynamics in the future, or the behavior monitoring result indicates that there is malicious behavior, the suspicious file will be regarded as a malicious file.
[0049] In the first embodiment, feature data is extracted from suspicious file samples, the dynamics of suspicious file samples are predicted to obtain dynamic prediction results, the propagation behavior of suspicious file samples is monitored to obtain behavior monitoring results, and malicious files are detected based on feature data, dynamic prediction results, and behavior monitoring results. Since this embodiment can accurately detect malicious files in the industrial internet by extracting features, making dynamic predictions, and monitoring the behavior of suspicious file samples, it can improve the security of the industrial internet.
[0050] Reference Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the malicious file detection method for the industrial internet of the present invention, based on the above. Figure 2 The first embodiment shown presents a second embodiment of the malicious file detection method for the industrial internet of the present invention.
[0051] In the second embodiment, the feature data is IPR feature data, and step S10 includes: Step S10': Extract IPR feature data from the suspicious document sample.
[0052] It should be understood that, in order to improve the accuracy of malicious file detection in the Industrial Internet, the feature data in this embodiment may specifically be IPR feature data.
[0053] It should be noted that IPR (i.e., I / O request packet) is a data structure in which an upper-layer user program sends user requests to a lower-layer I / O manager. When an upper layer sends a request to a lower layer, many fields in the IPR and its stack structure contain various information related to the current file behavior. By analyzing the IPR, the specific content of the user's request can be reversed.
[0054] Understandably, IPR feature data can be used to analyze the IRP sequences of the mapped file behavior of suspicious file samples.
[0055] In the second embodiment, step S20 includes: Step S20': Based on a preset bidirectional long short-term memory network model, predict the dynamics of the suspicious file sample to obtain dynamic prediction results.
[0056] It should be understood that, in order to improve the accuracy of dynamic prediction results, this embodiment introduces a preset bidirectional long short-term memory network model to dynamically predict suspicious file samples.
[0057] It should be noted that the bidirectional Long Short-Term Memory (LSTM) network model can be used to predict the dynamics of suspicious document samples.
[0058] In the second embodiment, a pre-defined bidirectional long short-term memory network model is additionally introduced to dynamically predict suspicious file samples, thereby improving the accuracy of dynamic prediction results.
[0059] In the second embodiment, step S30 includes: Step S301: Obtain the propagation scenario of the suspicious file sample.
[0060] It should be understood that, in practical applications, the propagation behavior of suspicious files varies in different scenarios. Therefore, in order to improve the accuracy of propagation behavior monitoring, this embodiment also monitors the propagation behavior of suspicious file samples based on the propagation scenario of the suspicious file samples, and obtains the behavior monitoring results.
[0061] It should be noted that the propagation scenario can be any network scenario in which a suspicious file is spread, such as an intranet scenario or an extranet scenario.
[0062] Step S302: Monitor the propagation behavior of the suspicious file sample based on the propagation scenario and obtain the behavior monitoring results.
[0063] It is understandable that different propagation scenarios correspond to different monitoring strategies. Therefore, monitoring the propagation behavior of suspicious file samples based on the propagation scenario and obtaining the behavior monitoring results can be achieved by finding the monitoring strategy corresponding to the propagation scenario and monitoring the propagation behavior of suspicious file samples based on the monitoring strategy.
[0064] It should be understood that finding the monitoring strategy corresponding to a propagation scenario can be done by searching a preset strategy table. This preset strategy table contains the correspondence between propagation scenarios and monitoring strategies, and this correspondence can be pre-defined.
[0065] In the second embodiment, a propagation scenario for obtaining suspicious file samples is disclosed, and the propagation behavior of suspicious file samples is monitored based on the propagation scenario to obtain behavior monitoring results. Since this embodiment also monitors the propagation behavior of suspicious file samples based on the propagation scenario of suspicious file samples to obtain behavior monitoring results, the accuracy of propagation behavior monitoring can be improved.
[0066] Furthermore, in order to obtain reliable behavior monitoring results when the propagation scenario is an intranet scenario, step S302 includes: When the propagation scenario is an intranet scenario, the file type, process parameters, and file path of the suspicious file sample are obtained; The propagation behavior of the suspicious file sample is monitored based on the file type, process parameters, and file path to obtain behavior monitoring results.
[0067] It should be understood that, in order to obtain reliable behavior monitoring results when the propagation scenario is an intranet scenario, this embodiment monitors the propagation behavior of suspicious file samples based on the file type, process parameters, and file path of the suspicious file samples.
[0068] It is understandable that monitoring the propagation behavior of suspicious file samples based on file type, process parameters, and file path can determine that a suspicious file sample is maliciously propagating when at least one of the file type, process parameters, and file path is missing.
[0069] Furthermore, in order to obtain reliable behavior monitoring results when the propagation scenario is an external network scenario, step S302 further includes: When the propagation scenario is an external network scenario, detect whether the feature data contains an anomaly identifier; Based on the detection results, the propagation behavior of the suspicious file samples is monitored to obtain behavioral monitoring results.
[0070] It should be understood that, in order to obtain reliable behavior monitoring results when the propagation scenario is an external network scenario, this embodiment monitors the propagation behavior of suspicious file samples by detecting whether the feature data contains abnormal identifiers.
[0071] It should be noted that, in order to improve the accuracy of transmission behavior monitoring, the feature data in this embodiment can specifically be IPR feature data. Anomaly indicators can be preset.
[0072] In the second embodiment, step S40 includes: Step S40': Detect malicious files based on the IPR feature data, the dynamic prediction results, and the behavior monitoring results.
[0073] It should be understood that when IPR feature data is malicious, or the dynamic prediction result indicates the existence of malicious dynamics in the future, or the behavior monitoring result indicates the existence of malicious behavior, the suspicious file will be treated as a malicious file.
[0074] Reference Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the malicious file detection method for the industrial internet of the present invention. Based on the above embodiments, the third embodiment of the malicious file detection method for the industrial internet of the present invention is proposed.
[0075] In the third embodiment, before step S10, the method further includes: Step S01: Identify suspicious files in the network to be detected using a preset probe.
[0076] It should be understood that in practical applications, even if industrial enterprises are not connected to the Industrial Internet, malicious files can still launch cyberattacks by moving laterally based on their location. Therefore, in order to effectively capture suspicious file samples, this embodiment also uses probes and honeypots to capture suspicious file samples.
[0077] It should be noted that the preset probe can be set in advance. In this embodiment, the lateral movement probe is used as an example for explanation.
[0078] Furthermore, to improve the accuracy of suspicious document detection, step S01 includes: Network information of the network to be detected is obtained through a preset probe, and the network information is analyzed. Based on the analysis results, the files were restored to obtain the suspicious files.
[0079] Understandably, in order to improve the accuracy of suspicious file detection, in this embodiment, network information of the network to be detected is first obtained through a preset probe, and the network information is analyzed. Based on the analysis results, the file is restored to obtain the suspicious file.
[0080] It should be noted that the network to be detected can be a network that requires malicious file detection for the Industrial Internet, for example, the Industrial Internet itself. Network information can be traffic information and / or log information; this embodiment does not impose any limitations on this.
[0081] It should be understood that analyzing network information and restoring files based on the analysis results to obtain suspicious files may involve first analyzing traffic information and / or log information to identify files with violations, and then restoring the files with violations to obtain suspicious files.
[0082] In specific implementations, for example, the lateral movement probe method can first distinguish the read request and response byte stream data based on the Message ID of the ServerMessage Block (SMB) network communication protocol header, then determine the file with the violation based on the byte stream data, and by exporting and merging the data field and the grouped byte stream data, the original file format of the file with the violation can be restored, and the suspicious file can be obtained.
[0083] Step S02: Induce the suspicious file to launch a network attack by using preset inducing resources, and obtain a sample of the suspicious file.
[0084] It should be noted that the preset induction resources can be set in advance. In this embodiment and other embodiments, a honeypot is used as an example for illustration.
[0085] It should be understood that honeypots are essentially a technique for deceiving attackers. By deploying decoy hosts, network services, or information, attackers are lured to attack them. This allows attackers to capture and analyze the attack behavior, understand the tools and methods used by the attackers, and infer their attack intentions and motives. This enables defenders to clearly understand the security threats they face and enhance the security protection capabilities of their actual systems through technical and management means.
[0086] Furthermore, in order to better induce suspicious files to launch cyberattacks, step S02 includes: Build virtual networks; The suspicious file is induced to launch a cyberattack using the virtual network and preset inducement resources, thereby obtaining a sample of the suspicious file.
[0087] It should be understood that, in order to better induce suspicious files to carry out cyberattacks, in this embodiment, a virtual network is first constructed, and the virtual network and honeypot are used to lure suspicious files to carry out cyberattacks at pre-set "vulnerabilities" to obtain suspicious file samples.
[0088] Understandably, in practice, virtual networks, weak passwords, and honeypots can be used to lure suspicious files for cyberattacks. Weak passwords, in particular, are passwords with low security levels that are easily exploited.
[0089] In the third embodiment, a method is disclosed to identify suspicious files in the network to be detected by using a preset probe, and to induce network attacks on the suspicious files by using preset inducement resources to obtain suspicious file samples. Since this embodiment captures suspicious file samples based on probes and honeypots, it is able to effectively capture suspicious file samples.
[0090] In the third embodiment, after step S40, the method further includes: Step S50: When a malicious file is detected, the malicious file is intercepted.
[0091] It should be understood that, in order to avoid harm caused by malicious files, in this embodiment, malicious files are intercepted when they are detected.
[0092] Understandably, intercepting malicious files can prevent them from continuing to spread on the network.
[0093] Step S60: Generate alarm information corresponding to the malicious file.
[0094] It should be understood that, in order to promptly notify users of the existence of malicious files, this embodiment also generates alarm information corresponding to the malicious files after intercepting them.
[0095] It is understandable that the alarm information corresponding to the generated malicious file could be a preset alarm message. This preset alarm message can be pre-set; for example, "Malicious file exists on the network, intercepted" could be used as the preset alarm message.
[0096] The third embodiment intercepts malicious files when they are detected and generates alarm information corresponding to the malicious files, thereby preventing malicious files from causing harm and promptly informing users of the existence of malicious files.
[0097] Furthermore, to facilitate users in understanding more information about malicious files, step S60 includes: Obtain the source and target addresses of the malicious file; Based on the source address and the target address, generate alarm information corresponding to the malicious file.
[0098] It should be understood that, in order to help users understand more information about malicious files, this embodiment can generate alarm information by combining the source address and target address of the malicious file.
[0099] It should be noted that the source address can be the address from which the malicious file is propagated, and the target address can be the address from which the malicious file is propagated.
[0100] It is understandable that generating alert information corresponding to malicious files based on source and destination addresses could involve writing the source and destination addresses into a preset alert template to generate the corresponding alert information. The preset alert template can be configured in advance.
[0101] Furthermore, this embodiment of the invention also proposes a storage medium storing an industrial internet malicious file detection program, which, when executed by a processor, implements the industrial internet malicious file detection method as described above.
[0102] In addition, refer to Figure 5 This invention also proposes a malicious file detection device for the industrial internet, which includes: a dynamic prediction module 10, a behavior monitoring module 20, and a file detection module 30. The data extraction module 10 is used to extract feature data from suspicious file samples.
[0103] It should be noted that suspicious file samples can be pre-set or obtained by the malicious file detection equipment of the Industrial Internet from the network to be detected; this embodiment does not impose any restrictions on this. The network to be detected can be any network that requires malicious file detection within the Industrial Internet, for example, the Industrial Internet itself.
[0104] It is understandable that extracting feature data from suspicious file samples can be based on data identifiers. These data identifiers are used to distinguish different data points.
[0105] The dynamic prediction module 20 is used to predict the dynamics of the suspicious file sample and obtain the dynamic prediction result.
[0106] It should be understood that, in order to determine whether a suspicious file will endanger network security in the future, this embodiment also predicts the dynamics of the suspicious file sample.
[0107] It is understandable that predicting the dynamics of suspicious file samples and obtaining dynamic prediction results can be achieved by using a pre-set prediction model to predict the dynamics of the suspicious file samples. The pre-set prediction model can be pre-configured to predict the file's dynamics; for example, the pre-set prediction model can be a neural network model.
[0108] The behavior monitoring module 30 is used to monitor the propagation behavior of the suspicious file sample and obtain behavior monitoring results.
[0109] It should be understood that, in order to determine whether the current propagation behavior of a suspicious file endangers network security, this embodiment also monitors the propagation behavior of the suspicious file sample.
[0110] It is understandable that monitoring the spread of suspicious document samples can involve obtaining information about the spread of suspicious document samples and monitoring the spread of suspicious document samples based on that information.
[0111] The file detection module 40 is used to detect malicious files based on the feature data, the dynamic prediction results, and the behavior monitoring results.
[0112] It should be understood that when the feature data is malicious, or the dynamic prediction result indicates that there will be malicious dynamics in the future, or the behavior monitoring result indicates that there is malicious behavior, the suspicious file will be regarded as a malicious file.
[0113] This embodiment discloses the extraction of feature data from suspicious file samples, the prediction of the dynamics of suspicious file samples to obtain dynamic prediction results, the monitoring of the propagation behavior of suspicious file samples to obtain behavior monitoring results, and the detection of malicious files based on feature data, dynamic prediction results, and behavior monitoring results. Because this embodiment can accurately detect malicious files in the industrial internet by extracting features, making dynamic predictions, and monitoring the behavior of suspicious file samples, it improves the security of the industrial internet.
[0114] Other embodiments or specific implementations of the malicious file detection device for the industrial internet described in this invention can be found in the above-described method embodiments, and will not be repeated here.
[0115] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0116] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.
[0118] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.
Claims
1. A method for detecting malicious files in the industrial internet, characterized in that, The malicious file detection method for the Industrial Internet includes the following steps: Feature data is extracted from suspicious file samples. The feature data is IPR feature data, which is obtained by analyzing the IRP sequence of the mapped file behavior of the suspicious file samples. The dynamics of the suspicious file samples are predicted to obtain dynamic prediction results; The propagation behavior of the suspicious file samples is monitored to obtain the behavior monitoring results; Malicious files are detected based on the feature data, the dynamic prediction results, and the behavior monitoring results. Prior to the step of extracting feature data from the suspicious file sample, the method further includes: The network information of the network to be detected is obtained by a preset lateral movement probe, and the network information is analyzed. Based on the Message ID in the service information block network communication protocol header, the read request and response byte stream data are distinguished. By exporting and merging the data field and the grouped byte stream data, the file is restored and the suspicious file is obtained. By using preset inducement resources to induce the suspicious files to launch a network attack, a sample of the suspicious files is obtained.
2. The malicious file detection method for the Industrial Internet as described in claim 1, characterized in that, The step of monitoring the propagation behavior of the suspicious file sample and obtaining the behavior monitoring results includes: Obtain the propagation scenario of the suspicious file sample; Based on the aforementioned propagation scenario, the propagation behavior of the suspicious file sample is monitored to obtain the behavior monitoring results.
3. The malicious file detection method for the Industrial Internet as described in claim 2, characterized in that, The step of monitoring the propagation behavior of the suspicious file sample based on the propagation scenario and obtaining the behavior monitoring results includes: When the propagation scenario is an intranet scenario, the file type, process parameters, and file path of the suspicious file sample are obtained; The propagation behavior of the suspicious file sample is monitored based on the file type, process parameters, and file path to obtain behavior monitoring results.
4. The malicious file detection method for the Industrial Internet as described in claim 2, characterized in that, The step of monitoring the propagation behavior of the suspicious file sample based on the propagation scenario and obtaining the behavior monitoring results includes: When the propagation scenario is an external network scenario, detect whether the feature data contains an anomaly identifier; Based on the detection results, the propagation behavior of the suspicious file samples is monitored to obtain behavioral monitoring results.
5. The malicious file detection method for the Industrial Internet as described in claim 1, characterized in that, The step of inducing the suspicious file to launch a network attack by using preset inducement resources to obtain a suspicious file sample includes: Build virtual networks; The suspicious file is induced to launch a cyberattack using the virtual network and preset inducement resources, thereby obtaining a sample of the suspicious file.
6. The method for detecting malicious files in the industrial internet as described in any one of claims 1 to 4, characterized in that, The step of dynamically predicting the suspicious file sample and obtaining the dynamic prediction result includes: The dynamic prediction of the suspicious file samples is obtained by using a preset bidirectional long short-term memory network model.
7. The method for detecting malicious files in the industrial internet as described in any one of claims 1 to 4, characterized in that, Following the step of detecting malicious files based on the feature data, the dynamic prediction results, and the behavior monitoring results, the method further includes: When a malicious file is detected, the malicious file is intercepted; Generate alarm information corresponding to the malicious file.
8. The malicious file detection method for the Industrial Internet as described in claim 7, characterized in that, The step of generating the alarm information corresponding to the malicious file includes: Obtain the source and target addresses of the malicious file; Based on the source address and the target address, generate alarm information corresponding to the malicious file.
9. A malicious file detection device for the industrial internet, characterized in that, The industrial internet malicious file detection device includes: a memory, a processor, and an industrial internet malicious file detection program stored on the memory and executable on the processor. When the industrial internet malicious file detection program is executed by the processor, it implements the industrial internet malicious file detection method as described in any one of claims 1 to 8.
10. A storage medium, characterized in that, The storage medium stores a malicious file detection program for the Industrial Internet, which, when executed by the processor, implements the malicious file detection method for the Industrial Internet as described in any one of claims 1 to 8.
11. A malicious file detection device for the Industrial Internet, characterized in that, The malicious file detection device for the industrial internet includes: a data extraction module, a dynamic prediction module, a behavior monitoring module, and a file detection module; The data extraction module is used to extract feature data from suspicious file samples. The feature data is IPR feature data, which is obtained by analyzing the IRP sequence of the mapped file behavior of the suspicious file samples. The dynamic prediction module is used to dynamically predict the suspicious file sample and obtain dynamic prediction results. The behavior monitoring module is used to monitor the propagation behavior of the suspicious file sample and obtain behavior monitoring results; The file detection module is used to detect malicious files based on the feature data, the dynamic prediction results, and the behavior monitoring results; The malicious file detection device for the industrial internet also includes: a sample acquisition module; The sample acquisition module is used to acquire network information of the network to be detected through a preset lateral movement probe, and analyze the network information; distinguish the read request and response byte stream data according to the Message ID of the service information block network communication protocol header, and restore the file by exporting and merging the data field and the group byte stream data to obtain the suspicious file; The sample acquisition module is also used to induce the suspicious file to launch a network attack through preset inducing resources, thereby obtaining a suspicious file sample.
12. The malicious file detection device for the Industrial Internet as described in claim 11, characterized in that, The behavior monitoring module is also used to obtain the propagation scenario of the suspicious file sample; The behavior monitoring module is also used to monitor the propagation behavior of the suspicious file sample based on the propagation scenario and obtain behavior monitoring results.
13. The malicious file detection device for the Industrial Internet as described in claim 12, characterized in that, The behavior monitoring module is also used to obtain the file type, process parameters and file path of the suspicious file sample when the propagation scenario is an intranet scenario; The behavior monitoring module is also used to monitor the propagation behavior of the suspicious file sample based on the file type, the process parameters, and the file path, and obtain behavior monitoring results.
14. The malicious file detection device for the Industrial Internet as described in claim 12, characterized in that, The behavior monitoring module is also used to detect whether the feature data contains an abnormal identifier when the propagation scenario is an external network scenario; The behavior monitoring module is also used to monitor the propagation behavior of the suspicious file sample based on the detection results, and obtain behavior monitoring results.
15. The malicious file detection device for the Industrial Internet as described in claim 11, characterized in that, The sample acquisition module is also used to construct a virtual network; The sample acquisition module is also used to induce the suspicious file to launch a network attack through the virtual network and preset inducement resources, thereby obtaining a suspicious file sample.
Citation Information
Patent Citations
Malicious code infection inducing information discrimination system, storage medium in which program is recorded and method
KR102093275B1
Detecting malware infestations in large-scale networks
US8959643B1
