Active defense method for Internet of Things equipment
By setting up a master manager, pre-trained model and terminal controller in the IoT device, generating camouflage information and bait traffic, creating camouflage instances, the active defense of IoT devices is realized, attracting attackers, reducing the risk of being attacked, and optimizing Administrator response process improves security and solves the lack of active defense and system complexity in the prior art.
Patent Information
- Application Number
- CN202411114899.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing IoT device security protection technology lacks active defense measures, making it difficult to effectively resist hackers' early information collection and attacks. The existing system is large in scale and difficult to deploy, and requires professional operation and maintenance, poor flexibility, and can only be detected after the attack occurs. And countermeasures, and cannot effectively prevent potential threats.
Set up the master manager, pre-trained model and terminal controller in the Internet of Things device to generate camouflage information and bait traffic, create camouflage instances, actively release bait traffic through camouflage policy actuators to attract attackers, and the interactive behavior recorder records interactive information , dynamically change the guise instance to attract the attention of the attacker and reduce the possibility of the attack success.
By actively releasing bait traffic and dynamically changing camouflage instances, it can attract attackers in the network environment, reduce the risk of being attacked, optimize the administrator's response process, reduce the system usage cost, improve security, and avoid administrators' energy to collect desensitized traffic. Prevent the reverse analysis of bait flow.
Smart Images

Figure CN119071043A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of Internet of Things security technology, and in particular to an active defense method for Internet of Things devices. Background Art
[0002] IoT devices have become potential targets for cyber attacks due to their network connectivity and ubiquity. However, due to hardware performance limitations and system differences, conventional equipment and software used to protect computer network security are difficult to apply to IoT devices. As a result, attacks against IoT devices are increasing.
[0003] Most IoT devices today have shortcomings such as using default credentials and weak passwords that make the devices more vulnerable to intrusion, lack of firmware updates and vulnerability fixes that make the devices vulnerable to known attacks, lack of encryption mechanisms, poor management of IoT devices that may lead to unauthorized devices accessing the network and increasing the risk of cyber attacks, and collecting a large amount of user data but users may lack transparency into the collection and use of this data, which raises privacy issues.
[0004] In view of the shortcomings of IoT devices, the existing technologies have proposed measures to ensure the security of IoT, mainly using strong passwords, multi-factor authentication, etc. to ensure that only authorized users can access the devices, timely applying security updates and patches provided by manufacturers to prevent known vulnerabilities from being exploited, implementing network traffic monitoring and intrusion detection systems to identify abnormal behaviors and take measures in a timely manner, using strong encryption standards in the transmission and storage stages to protect the confidentiality of data, and training users and device administrators on network security best practices to enhance awareness of potential threats. However, these measures are too passive. Only when the attacker launches an attack on the relevant IoT devices can these traditional means detect the attack behavior and begin to respond. However, this is not effective for hackers with increasingly powerful technology today. Today's hackers will collect as much information as possible before attacking the relevant terminal devices. Therefore, when the attack occurs, the attacker can complete his operation in a very short time and escape. Even if countermeasures are taken afterwards, it is difficult to make up for the damage it has caused.
[0005] In addition, through the existing IoT security protection products, such as Venustech's IoT security access protection system, Ahnheng Information's IoT security monitoring platform, and Topsec's IoT security access gateway, it can be seen that although most of the existing IoT security protection technologies are comprehensive protection systems that can involve protection systems and platforms, they involve asset management, blacklist and whitelist access control, traffic analysis and detection, data security transmission, malicious behavior perception and other aspects, but they still have obvious shortcomings. For example, after the existing IoT security protection products integrate various functions and tools, the system scale is large, deployment is difficult, and professional personnel are required to be responsible for daily operation and maintenance, and the flexibility of system application is poor; and many IoT device security detection platforms need to be connected with the user's various business function modules in detail during deployment. If the security platform that collects a large amount of user sensitive data has vulnerabilities, the risk of leakage of users' important data is relatively high. Moreover, although the existing IoT security protection system integrates various security tools, it is basically only possible to detect and counterattack after the attacker takes active offensive behavior. However, this does not have sufficient countermeasures for the attacker's early information collection and detection. Therefore, for some experienced hackers, these defense measures do not constitute much of an obstacle.
[0006] Therefore, it is necessary to provide an IoT device security protection method that can actively defend IoT devices to make up for the weaknesses in the field of IoT security protection. Summary of the invention
[0007] The purpose of the present invention is to provide an active defense method for an Internet of Things device, so as to make up for the weakness of active defense in the field of Internet security protection.
[0008] In a first aspect, the active defense method for an Internet of Things device provided by the present invention includes: setting a master control manager, a pre-trained model and a terminal controller in the Internet of Things device; the master control manager sets camouflage information, the camouflage information includes a camouflage configuration file and a camouflage strategy of the Internet of Things device; the pre-trained model generates bait traffic according to data information of the Internet of Things device; the terminal controller creates a camouflage instance according to the camouflage information and the bait traffic, assigns attribute information to the camouflage instance according to the camouflage configuration file, and switches the information of the camouflage instance according to the set rules according to the camouflage strategy; the camouflage instance includes a camouflage strategy executor and an interactive behavior recorder, the camouflage strategy executor is used to actively release bait traffic according to the camouflage strategy to attract attackers and interact with attackers, and the interactive behavior recorder is used to record interactive information.
[0009] The beneficial effect of the active defense method for the Internet of Things device provided by the present invention is: in a network environment, some real Internet of Things terminals are disguised by generating disguised instances and actively releasing bait traffic to attract attackers to interact, and by setting a disguised strategy to guide the disguised instances to interact and dynamically change with attackers, thereby attracting the attention of attackers to discover potential attackers. By guiding the dynamic changes of the honey spot terminal in response to attackers through the disguised strategy, the possibility of being breached by attackers can be reduced, and the process of manual changes by the administrator can be optimized. A pre-trained model is introduced for the generation of bait traffic, which avoids the administrator from spending more energy to collect desensitized traffic, and can prevent attackers from reverse analysis of the bait traffic, reducing the cost of using the system while also improving the security of the system.
[0010] In a possible embodiment, the data information of the Internet of Things device includes application layer business traffic data and industrial control instruction data of the Internet of Things device; the pre-trained model generates bait traffic based on the data information of the Internet of Things device, including: adjusting the pre-trained model according to the application layer business traffic data of the Internet of Things device to obtain a business data model, and the business data model is used to generate simulated Internet of Things data traffic as bait traffic; adjusting the pre-trained model according to the industrial control instruction data of the Internet of Things device to obtain an industrial control instruction model, and the industrial control instruction model is used to generate simulated industrial control instructions as bait traffic.
[0011] In another possible embodiment, the terminal controller switches the information of the camouflage instance according to the set rules based on the camouflage strategy, including: switching the attribute information of the camouflage instance according to the set rules, wherein the attribute information includes the IP address and port number; replacing the data information of the camouflage instance according to the set rules, wherein the data information includes sensitive data and information in the bait traffic.
[0012] In other possible embodiments, the masquerade policy executor is further configured to restart the masquerade instance and switch the service when there is no connection record for a masquerade instance within a set time.
[0013] In the second aspect, the present invention also provides an active defense device for an Internet of Things device, including a main control manager, a pre-trained model and a terminal controller; the main control manager sets camouflage information, the camouflage information includes a camouflage configuration file and a camouflage strategy of the Internet of Things device; the pre-trained model generates bait traffic based on the data information of the Internet of Things device; the terminal controller creates a camouflage instance based on the camouflage information and the bait traffic, assigns attribute information to the camouflage instance based on the camouflage configuration file, and switches the information of the camouflage instance according to the set rules based on the camouflage strategy; the camouflage instance includes a camouflage strategy executor and an interactive behavior recorder, the camouflage strategy executor is used to actively release bait traffic according to the camouflage strategy to attract attackers and interact with attackers, and the interactive behavior recorder is used to record interactive information.
[0014] The data information of the IoT device includes application layer business flow data and industrial control instruction data of the IoT device. The pre-trained model generates bait traffic according to the data information of the IoT device, including: adjusting the pre-trained model according to the application layer business flow data of the IoT device to obtain a business data model, the business data model is used to generate simulated IoT data traffic as bait traffic; adjusting the pre-trained model according to the industrial control instruction data of the IoT device to obtain an industrial control instruction model, the industrial control instruction model is used to generate simulated industrial control instructions as bait traffic.
[0015] The terminal controller switches the information of the disguised instance according to the set rules based on the disguise strategy, including: switching the attribute information of the disguised instance according to the set rules, wherein the attribute information includes the IP address and port number; replacing the data information of the disguised instance according to the set rules, wherein the data information includes sensitive data and information in the bait traffic.
[0016] The masquerade policy executor is also used to restart the masquerade instance and switch services when a masquerade instance has no connection records within a set time.
[0017] In a third aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the active defense method of the above-mentioned Internet of Things device is implemented.
[0018] In a fourth aspect, the present invention also provides an electronic device, comprising: a processor and a memory; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory, so that the electronic device executes the above-mentioned active defense method of the Internet of Things device.
[0019] For the beneficial effects of the second to fourth aspects, reference may be made to the description of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 A schematic diagram of a framework of an active defense method for an Internet of Things device provided by an embodiment of the present invention;
[0021] Figure 2 A schematic diagram of the structure of a master control manager provided by an embodiment of the present invention;
[0022] Figure 3 A schematic diagram of the structure of a pre-training model provided in an embodiment of the present invention;
[0023] Figure 4 A schematic diagram of the functional modules of a terminal controller provided by an embodiment of the present invention;
[0024] Figure 5A functional flow chart of a disguised example provided for an embodiment of the invention;
[0025] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0026] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be understood by people with general skills in the field to which the present invention belongs. "Including" and similar words used in this article mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects.
[0027] This embodiment provides an active defense method for an IoT security device, which is implemented by setting a master control manager, a pre-trained model, and a terminal controller in the IoT device. Figures 1 to 5 , the method comprising:
[0028] The master control manager sets the camouflage information, which includes the camouflage configuration and camouflage strategy of the IoT device.
[0029] The pre-trained model generates decoy traffic based on the data information of IoT devices.
[0030] The terminal controller creates a camouflage instance according to the camouflage information and the decoy traffic, allocates attribute information to the camouflage instance according to the camouflage configuration file, and switches the information of the camouflage instance according to the set rules according to the camouflage strategy.
[0031] The camouflage instance includes a camouflage strategy executor and an interaction behavior recorder. The camouflage strategy executor is used to actively release bait traffic to attract attackers and interact with attackers according to the camouflage strategy, and the interaction behavior recorder is used to record interaction information.
[0032] In a possible embodiment, the master control manager sets the camouflage information including: the master control manager obtains the camouflage configuration information input by the administrator, and generates a camouflage configuration file and a camouflage strategy for the IoT device according to the camouflage configuration information input by the administrator. Exemplarily, the camouflage configuration file includes terminal configuration information for generating a camouflage instance, such as the IP address, MAC address, developed port, and communication protocol used by the fake IoT device; the camouflage strategy includes a generation strategy for bait traffic, and the camouflage instance is an interaction strategy and a switching strategy for the camouflage instance.
[0033] In a possible embodiment, the camouflage information may be default camouflage information pre-set and stored in the master control manager, wherein the default camouflage information includes a default camouflage configuration file and a camouflage strategy. When the administrator does not input the camouflage configuration information, that is, the master control manager does not obtain the configuration information input by the administrator, the master control manager obtains the pre-stored default camouflage information for application.
[0034] See the instruction manual Figure 2 In a specific embodiment, the master control manager is set at the user level of the IoT device, and can be controlled by users and operation and maintenance personnel, and coordinates the active defense work of the IoT device through camouflage configuration files and camouflage strategies. The content of the camouflage configuration file includes the service of the specific terminal entity to be camouflaged and some basic information, such as IP address, MAC address and open ports. The camouflage strategy defines the behavior performed during the generation of each camouflage instance and after the camouflage instance is generated, including the generation strategy of bait traffic, the way and content of the interaction between the camouflage instance and the attacker, the data information of the actively released bait traffic, and the rules followed by the camouflage instance when dynamic transformation is required.
[0035] The specific form of the masquerade policy can be a template file or a database. The masquerade policy can be successfully created and applied only by the user or administrator editing the content of the masquerade policy file according to the template requirements specified by the system.
[0036] See the instruction manual Figure 3 In S102, in a possible embodiment, the pre-trained model is a model that can be used to generate a large amount of decoy traffic obtained by training with a pre-training data set, wherein the pre-training data set includes common traffic such as TCP traffic and UDP traffic. The pre-trained model includes a basic weight layer and an attention layer, and the basic weight layer generates traffic according to the basic weights set therein, wherein the basic weights are obtained by training the initialization model using the pre-training data set. The attention layer is used for subsequent transfer learning of the pre-trained model, and a specific task model that can be used in actual scenarios can be obtained through the application of the attention layer.
[0037] In a possible embodiment, the data information of the IoT device includes application layer business flow data and industrial control instruction data of the IoT device. The pre-trained model generates bait traffic according to the data information of the IoT device, including: adjusting the pre-trained model according to the application layer business flow data of the IoT device to obtain a business data model, the business data model is used to generate simulated IoT data traffic as bait traffic; adjusting the pre-trained model according to the industrial control instruction data of the IoT device to obtain an industrial control instruction model, the industrial control instruction model is used to generate simulated industrial control instructions as bait traffic.
[0038] In actual applications, according to specific needs, the application layer business traffic data set or the industrial control instruction data set is used to fine-tune the model to obtain a specific task model suitable for a specific scenario. The bait traffic generated by the generated specific task model is used to package and load into the disguised instance. For example, when there are many business servers in the application scenario, the application layer business traffic data is used to adjust the pre-trained model, and when there are many industrial control systems sending and receiving instructions in the application scenario, the industrial control instruction data is used to adjust the pre-trained model. When adjusting the pre-trained model, the basic weights of the pre-trained model are adjusted under the action of the attention layer, so that the final weights can be used to generate bait traffic in specific task scenarios.
[0039] The decoy traffic generated by the method described in the present invention is a highly simulated traffic of IoT device business traffic or industrial control instructions, which can be used to confuse attackers and interact with attackers. Generating decoy traffic in the above manner avoids administrators spending more energy to collect desensitized traffic, and can prevent attackers from reverse analyzing the decoy traffic, thereby reducing the cost of using the system while also improving the security of the system. In addition, compared with the single form of application in the prior art, most of them are false business traffic in the form of replacing key values in business data, or directly using the traffic of real business with a relatively long time. The use of decoy traffic generated by the method of the present application can solve the problem that the false business traffic of the prior art application can be easily identified when encountering experienced attackers, and even the problem that the attacker can infer the characteristics of the real business traffic due to the overly obvious business characteristics.
[0040] See the instruction manual Figure 4 In a possible embodiment, the terminal controller is used to generate a corresponding camouflage instance based on the content in the camouflage configuration file and the set camouflage strategy, and manage and control the generated camouflage instance. The terminal controller can load the corresponding pre-trained model and the generated bait traffic based on the camouflage strategy.
[0041] In a specific embodiment, the terminal controller combines the active defense concept of the honey spot to generate and control the camouflage instance, and a camouflage instance is equivalent to a honey spot terminal.
[0042] Exemplarily, the terminal controller can obtain the camouflage information of the master manager, create a corresponding camouflage instance based on the content in the camouflage configuration file in the camouflage information, and assign basic attributes to each camouflage instance, wherein the basic attributes include the IP address, open port number, and service type of the camouflage instance. The terminal controller can also load a pre-trained model according to actual conditions and encapsulate the bait traffic generated by the pre-trained model according to the data information of the IoT device into a specified format and load it into the corresponding camouflage instance. Based on the camouflage strategy in the camouflage information, the terminal controller is responsible for executing part of the strategy for switching the camouflage instance information, and assigning the camouflage strategy that needs to be executed by the camouflage instance to the corresponding camouflage instance.
[0043] In a possible embodiment, the terminal controller switches the information of the disguised instance according to the set rules based on the disguise strategy, including: switching the attribute information of the disguised instance according to the set rules, wherein the attribute information includes the IP address and port number; replacing the data information of the disguised instance according to the set rules, wherein the data information includes sensitive data and information in the bait traffic.
[0044] In a possible embodiment, the camouflage strategy assigned to the camouflage instance by the terminal controller and specifically executed by the camouflage instance includes an interactive strategy executed after the camouflage instance actively releases bait traffic to the outside to attract attackers to make continuous attempts and thereby record more attackers' behaviors; when a camouflage instance does not have any connection records within a set time, it restarts and switches the service.
[0045] See the instruction manual Figure 5 In one possible embodiment, the disguised instance is used to actively send out bait traffic based on its own disguised service to attract potential attackers to attempt attacks, and interact with the "hooked" attackers to a certain extent, recording all behaviors connected to itself and operations performed by the attacker.
[0046] Exemplarily, each disguise instance includes a disguise strategy executor and an interactive behavior recorder. The disguise strategy executor is used to execute the disguise strategy assigned to the disguise instance, including releasing bait traffic to the outside, and attracting attackers to make continuous attempts according to the set interactive strategy to record more attackers' behaviors; when the disguise strategy has no connection record within the set time, restart the disguise instance and switch the service. The interactive behavior recorder is used to record the behavior of initiating a connection to itself and all operations performed on the disguise instance. The information recorded by the interactive behavior recorder will be sent to the user layer master manager in the form of a log.
[0047] The active defense method for the Internet of Things device provided by the present invention provides an active defense method for the Internet of Things device that combines the active defense concept of the honey spot, which is different from the defense method for the Internet of Things device in the prior art. In the network environment, some real Internet of Things terminals are disguised by generating disguised instances and actively releasing bait traffic to attract attackers to interact. By setting a disguised strategy to guide the disguised instance to interact with the attacker and change dynamically, it is possible to attract the attention of the attacker to discover potential attackers. The honey spot terminal is guided by the disguised strategy to dynamically change freely when dealing with attackers, which can not only reduce the possibility of being hacked by attackers, but also optimize the process of manual changes by the administrator. A pre-trained model is introduced for the generation of bait traffic, which avoids the administrator from spending more energy to collect desensitized traffic, and can prevent attackers from reverse analysis of the bait traffic, thereby reducing the cost of using the system while also improving the security of the system.
[0048] The active defense method of the Internet of Things device proposed in the present invention is constructed in the Internet of Things device to be a lightweight Internet of Things security system, which can be quickly deployed in the Internet of Things device environment without affecting the user's business system while generating camouflage instances to attract potential attackers, which helps administrators to quickly discover and respond. The initialization of the method can be performed in detail by the administrator inputting the camouflage information or database set, or the configuration of the camouflage instance and the setting of the camouflage strategy can be selected in a relatively simple way through the API interface called by the upper layer. The configuration is relatively simple and can be operated without professional management personnel.
[0049] In addition, the active defense method of the Internet of Things device of the present invention is flexible in application and can be used in conjunction with other Internet of Things security products to better ensure the security of the Internet of Things.
[0050] The embodiment of the present invention also provides an active defense device for an Internet of Things device, which is used to implement the above method embodiment. The device includes a main control manager, a pre-trained model and a terminal controller.
[0051] The main control manager sets camouflage information, which includes a camouflage configuration file and a camouflage strategy of the IoT device.
[0052] The pre-trained model generates decoy traffic based on the data information of IoT devices.
[0053] The terminal controller creates a camouflage instance according to the camouflage information and the decoy traffic, allocates attribute information to the camouflage instance according to the camouflage configuration file, and switches the information of the camouflage instance according to the set rules according to the camouflage strategy.
[0054] The camouflage instance includes a camouflage strategy executor and an interaction behavior recorder. The camouflage strategy executor is used to actively release bait traffic to attract attackers and interact with attackers according to the camouflage strategy, and the interaction behavior recorder is used to record interaction information.
[0055] The data information of the IoT device includes application layer business flow data and industrial control instruction data of the IoT device. The pre-trained model generates bait traffic according to the data information of the IoT device, including: adjusting the pre-trained model according to the application layer business flow data of the IoT device to obtain a business data model, the business data model is used to generate simulated IoT data traffic as bait traffic; adjusting the pre-trained model according to the industrial control instruction data of the IoT device to obtain an industrial control instruction model, the industrial control instruction model is used to generate simulated industrial control instructions as bait traffic.
[0056] The terminal controller switches the information of the disguised instance according to the set rules based on the disguise strategy, including: switching the attribute information of the disguised instance according to the set rules, wherein the attribute information includes the IP address and port number; replacing the data information of the disguised instance according to the set rules, wherein the data information includes sensitive data and information in the bait traffic.
[0057] The masquerade policy executor is also used to restart the masquerade instance and switch services when a masquerade instance has no connection records within a set time.
[0058] All relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.
[0059] In other embodiments of the present application, the present application discloses an electronic device, such as Figure 6 As shown, the electronic device 100 may include: one or more processors 101; a memory 102; a display 103; one or more applications (not shown); and one or more computer programs 104, and the above components may be connected via one or more communication buses 105. The one or more computer programs 104 are stored in the above memory and are configured to be executed by the one or more processors 101, and the one or more computer programs 104 include instructions, which may be used to execute the various steps in the corresponding embodiments.
[0060] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0061] Each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units.
[0062] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as flash memory, mobile hard disk, read-only memory, random access memory, disk or optical disk.
[0063] The above is only a specific implementation of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed in the embodiment of the present application should be included in the protection scope of the embodiment of the present application. Therefore, the protection scope of the embodiment of the present application should be based on the protection scope of the claims.
Claims
1. An active defense method for an Internet of Things device, characterized in that: include: Set up the master manager, pre-trained model, and terminal controller in the IoT device; The master control manager sets camouflage information, wherein the camouflage information includes a camouflage configuration file and a camouflage strategy of the IoT device; The pre-trained model generates bait traffic according to the data information of the IoT device; The terminal controller creates a camouflage instance according to the camouflage information and the bait traffic, assigns attribute information to the camouflage instance according to the camouflage configuration file, and switches the information of the camouflage instance according to the set rules according to the camouflage strategy; The camouflage instance includes a camouflage strategy executor and an interactive behavior recorder. The camouflage strategy executor is used to actively release bait traffic to attract attackers and interact with attackers according to the camouflage strategy, and the interactive behavior recorder is used to record interactive information.
2. The method according to claim 1, characterized in that: The data information of the IoT device includes application layer service flow data and industrial control instruction data of the IoT device; The pre-trained model generates bait traffic according to the data information of the IoT device, including: Adjusting the pre-trained model according to the application layer service traffic data of the IoT device to obtain a service data model, wherein the service data model is used to generate simulated IoT data traffic as bait traffic; The pre-trained model is adjusted according to the industrial control instruction data of the Internet of Things device to obtain an industrial control instruction model, and the industrial control instruction model is used to generate simulated industrial control instructions as bait traffic.
3. The method according to claim 1, characterized in that The terminal controller switches the information of the camouflage instance according to the camouflage strategy and the set rules, including: Switch the attribute information of the camouflage instance according to the set rules, where the attribute information includes the IP address and port number; The data information of the disguised instance is replaced according to the set rules, wherein the data information includes sensitive data and information in the bait traffic.
4. The method according to claim 1, characterized in that: The camouflage strategy executor is also used to restart the camouflage instance and switch the service when there is no connection record for a camouflage instance within a set time.
5. An active defense device for an Internet of Things device, characterized in that: The device includes a main control manager, a pre-trained model and a terminal controller; The master control manager sets camouflage information, wherein the camouflage information includes a camouflage configuration file and a camouflage strategy of the IoT device; The pre-trained model generates bait traffic according to the data information of the IoT device; The terminal controller creates a camouflage instance according to the camouflage information and the bait traffic, assigns attribute information to the camouflage instance according to the camouflage configuration file, and switches the information of the camouflage instance according to the set rules according to the camouflage strategy; The camouflage instance includes a camouflage strategy executor and an interactive behavior recorder. The camouflage strategy executor is used to actively release bait traffic to attract attackers and interact with attackers according to the camouflage strategy, and the interactive behavior recorder is used to record interactive information.
6. The device according to claim 5, characterized in that The data information of the IoT device includes application layer service flow data and industrial control instruction data of the IoT device; The pre-trained model generates bait traffic according to the data information of the IoT device, including: Adjusting the pre-trained model according to the application layer service traffic data of the IoT device to obtain a service data model, wherein the service data model is used to generate simulated IoT data traffic as bait traffic; The pre-trained model is adjusted according to the industrial control instruction data of the Internet of Things device to obtain an industrial control instruction model, and the industrial control instruction model is used to generate simulated industrial control instructions as bait traffic.
7. The device according to claim 5, characterized in that The terminal controller switches the information of the camouflage instance according to the camouflage strategy and the set rules, including: Switch the attribute information of the camouflage instance according to the set rules, where the attribute information includes the IP address and port number; The data information of the disguised instance is replaced according to the set rules, wherein the data information includes sensitive data and information in the bait traffic.
8. The device according to claim 5, characterized in that The camouflage strategy executor is also used to restart the camouflage instance and switch the service when there is no connection record for a camouflage instance within a set time.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the active defense method for an Internet of Things device according to any one of claims 1 to 4 is implemented.
10. An electronic device, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory so that the electronic device executes the active defense method for an Internet of Things device according to any one of claims 1 to 4.
Citation Information
Patent Citations
Security defense method, gateway proxy device and storage medium
CN116471121A
Network camera honey point generation method and device based on active defense
CN118075035A
Method and system for improving defensiveness of industrial control protocol intrusion detection model
CN118400138A
High-Fidelity Model-Driven Deception Platform for Cyber-Physical Systems
US20200076850A1
