Method and related device for locating and mitigating crosstalk attacks in a classical quantum hybrid transmission network

Abstract

The present application provides a method and related device for locating and mitigating crosstalk attacks in a classical quantum hybrid transmission network. The method includes: inputting the transmission signal of the current classical quantum hybrid link into a pre-trained supervised learning model to obtain the crosstalk type corresponding to the transmission signal being crosstalked by an attack signal; constructing a positioning auxiliary graph corresponding to the crosstalk type based on the crosstalk type; determining the wavelength channel where the attack point and / or attack range of the crosstalk is located based on the positioning auxiliary graph, constructing a rerouting topology for the transmission signal based on the priority of the transmission signal crosstalked by the crosstalk type, and adjusting the network traffic distribution, so as to complete the location of the crosstalk introduced in the transmission signal of the classical quantum hybrid link and perform rerouting.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a method for locating and mitigating crosstalk attacks in a classical quantum hybrid transmission network and related devices. Background Art

[0002] Based on the Heisenberg uncertainty and single-photon unclonable theorems in quantum mechanics, quantum key distribution (QKD) has become one of the most secure key negotiation schemes under the current information technology background. Compared with traditional cryptography, QKD can detect any eavesdropping behavior during the key negotiation process, and thus is expected to provide long-term security for future communication systems that can overcome the deciphering ability of quantum computing. Currently, without building additional physical infrastructure, the common fiber transmission technology provides an effective solution to enable QKD networks, and has become the main form of current QKD commercialization. However, less consideration is given to the overall system security during the system integration process, and the security vulnerabilities existing in the fiber optic system itself will pose a threat to QKD applications. Therefore, many security vulnerabilities in the existing common fiber transmission system may be maliciously exploited. On the one hand, it damages the performance of the original classical communication channel, and on the other hand, it damages the performance of the introduced quantum channel, preventing the normal progress of the key negotiation process. This is because the weak characteristics of quantum signals make them more sensitive to attack behaviors that introduce additional power signals in the classical network, such as enhanced Raman scattering interference. These vulnerabilities may prevent the classical / quantum hybrid network from operating normally. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose a method for locating and mitigating crosstalk attacks in a classical quantum hybrid network, which can effectively reduce the crosstalk impact caused by attack signals.

[0004] Based on the above purpose, in the first aspect, this application provides a method for locating and mitigating crosstalk attacks in a classical quantum hybrid network, including:

[0005] Inputting the transmission signal of the current classical quantum hybrid link into a pre-trained supervised learning model to obtain the crosstalk type corresponding to the transmission signal being crosstalked by an attack signal; wherein, the current classical quantum hybrid link includes multiple wavelength channels, and the multiple wavelength channels are used to transmit the transmission signal;

[0006] Based on the crosstalk type, constructing a positioning auxiliary graph corresponding to the crosstalk type, and based on the positioning auxiliary graph, determining the wavelength channel where the attack point and / or attack range of the crosstalk is located, wherein the positioning auxiliary graph includes the path and node set through which the crosstalked transmission signal passes;

[0007] Construct a rerouting topology for the transmission signal based on the priority of the transmission signal affected by the crosstalk of the crosstalk type, and adjust the network traffic distribution, where the wavelength channels corresponding to the attack points and / or attack ranges of the crosstalk are deleted in the rerouting topology.

[0008] Optionally, the crosstalk type includes: in-channel crosstalk, inter-channel crosstalk, and Raman scattering crosstalk;

[0009] Inputting the transmission signal of the current classical quantum hybrid link into a pre-trained supervised learning model to obtain the crosstalk type corresponding to the transmission signal includes:

[0010] If the central wavelength of the wavelength channel where the attack signal is located is the same as or overlaps with the central wavelength of the wavelength channel where the transmission signal of the current classical quantum hybrid link is located, it is determined as in-channel crosstalk;

[0011] If the central wavelength of the wavelength channel where the attack signal is located is adjacent to the central wavelength of the wavelength channel where the transmission signal of the current classical quantum hybrid link is located, it is determined as inter-channel crosstalk;

[0012] If the attack signal generates Raman scattering on the quantum signal in the transmission signal of the current classical quantum hybrid channel, it is determined as Raman scattering crosstalk.

[0013] Optionally, the positioning assistance graph further includes: a first positioning assistance graph, a second positioning assistance graph, and a third positioning assistance graph;

[0014] Constructing a positioning assistance graph corresponding to the crosstalk type based on the crosstalk type includes:

[0015] Based on the crosstalk type being in-channel crosstalk, select the interrupted transmission signals affected by the in-channel crosstalk, and construct the first positioning assistance graph according to the positions divided by the paths and wavelength channels passed by the head node and the tail node of the interrupted transmission signal;

[0016] Based on the crosstalk type being inter-channel crosstalk, select the damaged transmission signals affected by the inter-channel crosstalk, and select the adjacent wavelength channels on the overlapping path of the path passed by the damaged transmission signal and the path passed by the interrupted transmission signal to construct the second positioning assistance graph;

[0017] Based on the crosstalk type being Raman scattering crosstalk, select the quantum signals affected by the Raman scattering crosstalk, and select the wavelength channels where the range of the attack signal wavelength is located on the overlapping path of the damaged transmission signal and the quantum signals affected by the Raman scattering crosstalk to construct the third positioning assistance graph.

[0018] Optionally, determining the attack point and / or attack range of the crosstalk based on the positioning assistance graph includes:

[0019] Compare the first positioning assistance graph with the third positioning assistance graph. In response to the wavelength channels on the overlapping path of the first positioning assistance graph and the third positioning assistance graph being the same, the attack range is the link set of the traffic input at the tail node of the overlapping path in the first positioning assistance graph;

[0020] In response to the wavelength channels on the overlapping path of the first positioning assistance graph and the third positioning assistance graph being different, the attack range of the attack signal is the link set of the traffic input at the head node of the overlapping path in the first positioning assistance graph.

[0021] Optionally, constructing a rerouting topology for the transmission signal based on the priority of the transmission signal affected by the crosstalk type and adjusting the network traffic distribution includes:

[0022] Construct a rerouting topology for the transmission signal with high priority that is affected by the crosstalk, where the attack point of the crosstalk and / or the wavelength channel where the attack range is located are deleted in the rerouting topology;

[0023] Adjust the network traffic distribution, and adjust the quantum signal in the transmission signal affected by the crosstalk to be carried on the wavelength channel with the farthest interval from the wavelength channel where the classical signal is located and the wavelength channel where the attack signal is located.

[0024] Optionally, the priority of the transmission signal affected by the crosstalk type is configured such that the interrupted transmission signal affected by the in-channel crosstalk takes precedence over the impaired transmission signal affected by the inter-channel crosstalk takes precedence over the quantum signal affected by Raman scattering crosstalk.

[0025] Optionally, the pre-trained supervised learning model is further used to output the relationship between the channel interval of the wavelength channel and the crosstalk value, for calculating the channel interval between the wavelength channel where the attack signal is located and the wavelength channel where the quantum signal is located;

[0026] Locate the attack signal based on the channel interval between the wavelength channel where the attack signal is located and the wavelength channel where the quantum signal is located.

[0027] In a second aspect, the present application provides a crosstalk attack positioning and mitigation device for a classical-quantum hybrid transmission network, including:

[0028] A supervised learning analysis module, configured to analyze the crosstalk type corresponding to the transmission signal of the currently obtained classical-quantum hybrid link;

[0029] An attack positioning module, configured to construct a positioning assistance graph corresponding to the crosstalk type according to the crosstalk type, and determine the attack point and / or attack range of the crosstalk;

[0030] An attack mitigation module, configured to construct a rerouting topology of the transmission signal according to the priority of the transmission signal affected by crosstalk of the crosstalk type, delete the attack point and / or attack range of the crosstalk and adjust the network traffic distribution.

[0031] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method described above when executing the program.

[0032] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method described above.

[0033] As can be seen from the above, the crosstalk attack location and mitigation method and related devices provided by the present application use a pre-set supervised learning model as a diagnostic tool to determine the crosstalk type. According to the crosstalk type, a positioning auxiliary graph corresponding to the crosstalk type is constructed, and the positioning auxiliary graph is used to effectively determine the position of the attack signal in the current classical quantum hybrid link, so as to perform rerouting and adjust the network traffic distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following will briefly introduce the drawings required for use in the embodiments or related technology descriptions. Obviously, the drawings in the following descriptions are only embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0035] Figure 1 It is a flowchart of a method for locating and mitigating crosstalk attacks in a classical quantum hybrid network according to an embodiment of the present application;

[0036] Figure 2 It is a schematic diagram of supervised learning of a supervised learning model according to an embodiment of the present application;

[0037] Figure 3 It is a schematic diagram of a supervised learning model based on a recurrent neural network according to an embodiment of the present application;

[0038] Figure 4 It is a schematic diagram of a scenario where a transmission signal is affected by an attack signal crosstalk according to an embodiment of the present application;

[0039] Figure 5a It is a schematic diagram of a first positioning auxiliary graph according to an embodiment of the present application;

[0040] Figure 5b It is a schematic diagram of a first positioning auxiliary graph according to an embodiment of the present application;

[0041] Figure 5c This is a schematic diagram of the first positioning assistance figure in the embodiment of the present application;

[0042] Figure 6 This is a schematic diagram of the rerouting topology of the transmission signal affected by crosstalk in the embodiment of the present application;

[0043] Figure 7 This is a schematic diagram of a device for positioning and mitigating crosstalk attacks in a classical quantum hybrid transmission network in the embodiment of the present application;

[0044] Figure 8 This is a schematic diagram of the hardware structure of a specific electronic device in the embodiment of the present application. Detailed implementation manners

[0045] To make the objectives, technical solutions, and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to specific embodiments and the accompanying drawings.

[0046] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the ordinary meanings understood by those of ordinary skill in the field to which the present application belongs. The "first", "second", and similar terms used in the embodiments of the present application do not denote any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0047] This application focuses on the channel-level security vulnerabilities generated during the integration of QKD and optical fiber communication infrastructure, as well as the corresponding countermeasures. Specifically, in the scenario of co-fiber transmission between a classical optical network and a quantum key distribution network, it aims to effectively locate and mitigate the performance interference of crosstalk attacks by maliciously injected high-power signals on the hybrid transmission system. Specifically, on the one hand, existing QKD hybrid transmission systems do not have synchronous security considerations while paying attention to transmission performance. Attack behaviors that have been proven to exist in classical optical network scenarios can still pose threats to hybrid transmission systems, and their threat is more damaging to weak quantum signals. The crosstalk generated by malicious signals will damage both classical and quantum signals simultaneously, resulting in the failure of the data communication and QKD key generation processes. In the case where such attacks cause an increase in the classical / quantum bit error rate (BER / QBER), it is easy to confuse with eavesdropping behavior when using traditional diagnostic strategies for index determination. On the other hand, based on the technical background of the integrated transmission of quantum signals and classical signals in a single-mode optical fiber, such as co-fiber bearing in the C band, or bearing in the O band and C band respectively, the introduction of quantum signals requires network operators to make corresponding adjustments and upgrades to traditional network diagnostic schemes. For example, the traditional fiber damage location scheme using an optical time domain reflectometer (OTDR) is no longer applicable to the hybrid channel of quantum and classical signals. This requires the hybrid transmission network to further collect and report monitoring information from different channel spaces (classical-quantum hybrid channels) and different signal strengths simultaneously, increasing the difficulty and cost of network security protection monitoring. Therefore, there is an urgent need to design a countermeasure scheme for the attack threats existing in the hybrid transmission network.

[0048] Related research has not yet addressed the security issues of classical / quantum hybrid networks, especially crosstalk and signal degradation caused by the power difference between strong and weak signals. Due to the "weak" characteristics of quantum signals compared to traditional optical signals, they are more vulnerable to crosstalk effects such as background noise brought by high-power signals. Therefore, aiming at the security vulnerabilities existing in this classical-quantum hybrid network, this application uses a pre-set supervised learning model as a crosstalk diagnosis tool, and through the monitoring of performance indicators by the classical / quantum network, traces the source of the attack in a timely manner and takes network mitigation measures.

[0049] Reference Figure 1 , this application provides a method for locating and mitigating crosstalk attacks in a classical-quantum hybrid network, and the method includes:

[0050] S101. Input the transmission signal of the current classical-quantum hybrid link into a pre-trained supervised learning model to obtain the crosstalk type corresponding to the transmission signal being crosstalked by an attack signal.

[0051] It is understandable that a classical quantum hybrid link includes a classical link and a quantum link. The classical quantum hybrid link includes multiple wavelength channels, which respectively include multiple classical wavelength channels for transmitting classical signals on the classical link and multiple quantum wavelength channels for transmitting quantum signals on the quantum link. There is inherent crosstalk in the transmitted signals of the classical quantum hybrid link itself. That is to say, without the introduction of an attack signal, its inherent crosstalk will not affect the transmission of classical signals in the classical wavelength channels and the quantum key distribution task in the quantum wavelength channels. However, after an attack signal is introduced into the current classical quantum hybrid link, it will damage the performance of the classical wavelength channels and, at the same time, damage the key distribution task of the quantum wavelength channels, preventing the normal progress of the key negotiation process. Then, it is necessary for the preset supervised learning model to first be able to diagnose whether the current classical quantum hybrid link is affected by the crosstalk introduced by the attack signal.

[0052] Furthermore, first obtain the transmission signal of the current classical quantum hybrid channel and input it into the pre-trained supervised learning model, and output the crosstalk type of the transmission signal of the current classical quantum hybrid channel and the channel interval between the wavelength channel where the attack signal is located and the wavelength channel where the quantum signal is located.

[0053] Specifically, when crosstalk is transmitted along with the transmission signal on the classical quantum link, numerically it is reflected in the bit error rate at the classical signal receiver, the number of crosstalk photons at the quantum signal receiver, etc. Usually, the classical bit error rate (BER) and the quantum bit error rate (QBER) are used as network performance monitoring indicators. When the pre-trained supervised learning model obtains the transmission signal, it first extracts the classical bit error rate and the quantum bit error rate in real time from each receiving node on the current classical quantum hybrid link. For example Figure 4 extracted from nodes 3, 5, 7, and 8 as shown. When there is no crosstalk from the attack signal, extract the mathematical relationship between the normal parameter configuration and the damage value, and use this mathematical relationship as the nominal value of the inherent crosstalk. As Figure 2 shown, the crosstalk of these attack signals includes rate damage and the proportion of photon detection failure cases. The supervised learning algorithm distinguishes the inherent crosstalk and the crosstalk possibly introduced by the attack signal according to the previously extracted mathematical relationship between the parameter configuration and the damage value.

[0054] As Figure 3As shown, the pre-trained supervised learning model also includes a recurrent neural network. When the transmission signal passes through the recurrent neural network, the recurrent neural network analyzes the crosstalk type corresponding to the crosstalk introduced by the possible attack signal in the transmission process of the current classical quantum hybrid link transmission signal. The recurrent neural network can be respectively applied to the analysis of classical signal and quantum signal transmission. Specifically, for the supervised learning model based on the recurrent neural network, the classical signal crosstalk types are mainly in-channel crosstalk and inter-channel crosstalk. In terms of crosstalk value, in-channel crosstalk > inter-channel crosstalk > inherent crosstalk. Through data regression and crosstalk classification, the shared hidden layer is used to complete the data classification task, so as to distinguish whether the crosstalk type corresponding to the current attack signal is in-channel crosstalk or inter-channel crosstalk; for the supervised learning model based on the recurrent neural network, the crosstalk type of quantum signal is mainly Raman scattering crosstalk, and the crosstalk value changes with the increase of the interval between the classical wavelength channel and the quantum wavelength channel. Through the above pre-trained supervised learning model, it is judged whether the transmission signal is crosstalked by the attack signal during the transmission process, and the crosstalk is analyzed to determine the crosstalk type.

[0055] Further, the crosstalk of the classical quantum hybrid link mainly includes three categories:

[0056] In-channel crosstalk: If the central wavelength of the wavelength channel where the attack signal is located is the same as or overlaps with the central wavelength of the wavelength channel where the transmission signal is located, then it can be determined as in-channel crosstalk. This type of crosstalk has a large intensity and can interrupt the transmission signal;

[0057] Inter-channel crosstalk: If the central wavelength of the wavelength channel where the attack signal is located is adjacent to the central wavelength of the wavelength channel where the transmission signal is located, then it can be determined as inter-channel crosstalk. This type of crosstalk has a small intensity and only damages the quality of classical signals, but can greatly reduce the quantum signal key generation efficiency and inhibit the key negotiation performance of quantum signals in the quantum link.

[0058] Raman scattering crosstalk: If the attack signal generates Raman scattering on the quantum signal, it is determined as Raman scattering crosstalk.

[0059] Further, the pre-trained supervised learning model also outputs the relationship between the wavelength channel where the attack signal is located and the crosstalk value. According to the relationship between the wavelength channel where the attack signal is located and the crosstalk value, the channel interval between the wavelength channel where the attack signal is located and the wavelength channel where the quantum signal is located is deduced.

[0060] S102. Based on the crosstalk type, construct a positioning auxiliary graph corresponding to the crosstalk type, and based on the positioning auxiliary graph, determine the wavelength channel where the attack point and / or attack range of the crosstalk is located.

[0061] In some embodiments, as shown in Figures 5a - 5c the positioning auxiliary graph includes: a first positioning auxiliary graph, a second positioning auxiliary graph, and a third positioning auxiliary graph;

[0062] Based on the output of a pre-trained supervised learning model being in-channel crosstalk, select the interrupted transmission signals affected by in-channel crosstalk, and construct a first positioning assistance graph according to the path from the source to the destination and the wavelength channel division positions. It should be noted that the positioning assistance graph includes the paths and node sets of the transmission signals affected by crosstalk, and the source to the destination refers to the head node to the tail node of the transmission signal in the classical quantum link.

[0063] Based on the output of a pre-trained supervised learning model being inter-channel crosstalk, select the damaged transmission signals affected by inter-channel crosstalk. On the basis of the first positioning assistance graph, select adjacent wavelength channels on the overlapping path of the path of the interrupted transmission signal and the path of the damaged transmission signal, and construct a second positioning assistance graph.

[0064] Based on the output of a pre-trained supervised learning model being Raman scattering crosstalk, select the quantum signals affected by Raman scattering crosstalk. On the basis of the second positioning assistance graph, select the wavelength channels within the range of the attack signal wavelength on the overlapping path of the damaged transmission signal and the quantum signals affected by Raman scattering crosstalk, and construct a third positioning assistance graph.

[0065] It should be noted that through the relationship between the wavelength channel where the attack signal is located and the crosstalk value output by the pre-trained supervised learning model, according to the relationship between the wavelength channel where the attack signal is located and the crosstalk value, deduce the channel interval between the wavelength channel where the attack signal is located and the wavelength channel where the quantum signal is located, locate the wavelength channel where the attack signal is located, exclude the wavelength channels not crosstalked by the attack signal, and construct the first positioning assistance graph, the second positioning assistance graph and the third positioning assistance graph to prepare for subsequent rerouting and adjust the network traffic distribution.

[0066] Furthermore, determine the attack points and / or attack ranges of crosstalk according to the obtained first positioning assistance graph, second positioning assistance graph and third positioning assistance graph, specifically including:

[0067] Compare the first positioning assistance graph and the third positioning assistance graph. If the wavelength channels on the overlapping path of the paths of the transmission signals of the two are the same, the attack range of the attack signal is the link set of the tail node traffic input on the overlapping path in the first positioning assistance graph.

[0068] Compare the first positioning assistance graph and the third positioning assistance graph. If the wavelength channels on the overlapping path of the paths of the transmission signals of the two are different, the attack range of the attack signal is the link set of the head node traffic input on the overlapping path in the first assistance graph.

[0069] S103. Construct a rerouting topology for the transmission signals based on the priority of the transmission signals affected by the crosstalk type of crosstalk, and adjust the network traffic distribution.

[0070] In some embodiments, the mitigation strategies are first prioritized, that is, the priorities of the transmission signals affected by crosstalk of a certain type are divided. In the present application, the priorities of the transmission signals affected by crosstalk of a certain type are configured such that the interrupted transmission signals affected by in-channel crosstalk have a higher priority than the impaired transmission signals affected by inter-channel crosstalk, which in turn have a higher priority than the quantum signals affected by Raman scattering crosstalk.

[0071] A rerouting topology is constructed for the crosstalk-affected transmission signals with high priorities, the wavelength channels where the attack points and / or attack ranges are located are deleted, the network traffic distribution is adjusted, and under this rerouting topology, the quantum signals among the crosstalk-affected transmission signals are adjusted to the wavelength channels with the largest distance interval from the wavelength channels where the classical channels are located and the wavelength channels where the attack signals are located for carrying, so as to avoid the influence brought by the scattering crosstalk of classical signals.

[0072] In some embodiments, as Figure 4 shown, it is a schematic diagram of the crosstalk suffered by the quantum key distribution of quantum signals. In this scenario, it is considered that 4 transmission signals of a classical-quantum hybrid link are simultaneously transmitted within an 8-node topology. Each path has 40 wavelength channel resources, each node has the ability to transmit and receive quantum signals, and the distance between the quantum signal source and the destination node is appropriate, and no intermediate node is required to perform key relaying. Specifically, the transmission signal paths, the attack signals, and their wavelength channel allocations are shown in Table 1.

[0073] Table 1 Path and Wavelength Channel Allocation Table for Services 1-4 and Interference Signals

[0074] Transmission signal Path Classical wavelength channel Quantum wavelength channel 1 2→3→6→7 28，29，30，31，32 8，9，10 2 3→6→5 32，33，34，35，36 3，4，5，6，7 3 1→3→6→8 37，38，39，40 11，12，13，14，15 4 4→3→6→8 24，25，26，27，28 1，2 Attack signal Middle position between 1 - 3 34，35，36，37，38 None

[0075] Referring to Figure 4 and Table 1, malicious operations by an attacker introduce attack signals into Paths 1-3. The wavelengths of the attack signals cover wavelength channels #34-#38. Therefore, the introduced attack signals will cause in-channel crosstalk (wavelength channels #37, #38) to the transmission signal 3 (1→3→6→8) and then be transmitted to subsequent paths (3→6→8), where #34-#36 will be filtered out during the demultiplexing / multiplexing process at Node 3.

[0076] Specifically, as Figure 6As shown in Figure 2, according to the priority of the mitigation strategy, the transmission signal 3 affected by the intra-channel crosstalk is rerouted. According to the wavelength consistency restriction, the classical signals #37-#40 are rerouted to #20-#23 to avoid the wavelength conflict between path 3→6 and the transmission signals 1, 2, and 4. The wavelength channel where the quantum signal is located is the farthest from the wavelength channel where the classical signal and the attack signal are located in the available channels, so no adjustment is required. If the wavelength channel where the quantum signal is located is not the farthest from the wavelength channel where the classical signal and the attack signal are located in the available channels, then the quantum signal is adjusted to the available channel farthest from the wavelength channel where the classical signal and the attack signal are located. At this point, the network mitigation strategy is completed, and the updated network transmission signal carrying situation is shown in Table 2.

[0077] Specifically, refer to Figure 4 , abnormal crosstalk is detected at nodes 5, 7, and 8 respectively, and the preset supervised learning model classifies the crosstalk, specifically:

[0078] Node 5 detects that the classical signal of transmission signal 2 is subject to inter-channel crosstalk at #36, and the quantum signal is subject to Raman scattering crosstalk, and the crosstalk value corresponds to 19 wavelength channel spacing;

[0079] Node 7 detects that the classical signal of transmission signal 1 is not significantly damaged, but the quantum signal is subject to scattering crosstalk, and its crosstalk value corresponds to 27 wavelength channel spacing;

[0080] Node 8 detects that the classical signal of transmission signal 3 has no significant damage, and the quantum signal is subject to scattered crosstalk, and its crosstalk value corresponds to 35 wavelength channel intervals. At the same time, it detects that the classical signal of transmission signal 4 is subject to intra-channel crosstalk (cannot be received normally), and the quantum signal is subject to scattered crosstalk, and its crosstalk value corresponds to 19 wavelength channel intervals.

[0081] Specifically, refer to Figures 5a - 5c , construct the first positioning auxiliary map, the second positioning auxiliary map and the third positioning auxiliary map, wherein according to the output result of the preset supervised learning model, for the intra-channel crosstalk, select the interrupted transmission signal 3 affected by the intra-channel crosstalk, and construct the first positioning auxiliary map according to the path from the source to the sink and the wavelength channel division position, and the wavelength channel where the attack signal is located is located as #37, #38;

[0082] For the crosstalk between channels, the damaged transmission signal 2 affected by the crosstalk between channels is selected. On the basis of the first positioning auxiliary diagram, the adjacent wavelength channels are selected on the overlapping path of the interrupted transmission signal and the damaged transmission signal to construct the second positioning auxiliary diagram. The wavelength channel where the attack signal is located is located as #37.

[0083] For Raman scattering crosstalk, select quantum signals 1, 2, 3, and 4 that are subject to Raman scattering crosstalk. On the basis of the second positioning auxiliary map, select the wavelength channel where the wavelength range of the attack signal on the path where the damaged transmission signal and the quantum signal subject to Raman scattering crosstalk overlap is located, and obtain the result [#37, #37, #34, #37] to form the third positioning auxiliary map. At this point, the positioning auxiliary map is completed.

[0084] Specifically, the attack point and / or attack range of the crosstalk are determined according to the obtained first positioning auxiliary map, the second positioning auxiliary map, and the third positioning auxiliary map, and the attack point and / or attack range of the crosstalk are determined by comparing Figure 5a and Figure 5c , on the overlapping path 3→6, if the wavelength channels on the overlapping paths of the two transmission signals are consistent, then there is scattering crosstalk on wavelength channels #34 and #37. Therefore, it is determined that the path range where the attack signal is located is 1→3→6, and the range of the wavelength channel where the attack signal is located is #34-#38.

[0085] Furthermore, compared Figure 5a and Figure 5c , since the transmission signal 3 is subject to intra-channel crosstalk in wavelength channels [#37, #38], and the transmission signal 2 on path 3→6 is not subject to intra-channel crosstalk in wavelength channels #34-#36, that is, Figure 5a and Figure 5c The wavelength channels affected by crosstalk on the overlapping paths are inconsistent, so the attack range is Figure 5a The first node input traffic link set of the middle path 3→6 is 1→3, and the wavelength channel range of the attack signal is #34-#38.

[0086] In some embodiments, Figure 6 As shown in Figure 2, based on the priority of the transmission signal affected by the crosstalk type, the rerouting topology of the transmission signal is constructed, and the network traffic distribution is adjusted. According to the priority of the mitigation strategy, the transmission signal 3 affected by the crosstalk in the channel is rerouted. According to the wavelength consistency restriction, its classical signals #37-#40 are rerouted to #20-#23 to avoid the wavelength conflict between path 3→6 and the transmission signals 1, 2, and 4. The wavelength channel where the quantum signal is located is the farthest from the wavelength channel where the classical signal and the attack signal are located in the available channels, so no adjustment is required. If the wavelength channel where the quantum signal is located is not the farthest from the wavelength channel where the classical signal and the attack signal are located in the available channels, then the quantum signal is adjusted to the available channel farthest from the wavelength channel where the classical signal and the attack signal are located. At this point, the network mitigation strategy is completed, and the updated network transmission signal carrying situation is shown in Table 2.

[0087] Table 2 Paths and wavelength channel allocations of transmission signals 1-4 and attack signals after mitigation strategy

[0088] Transmission signal Path Classical wavelength channel Quantum wavelength channel 1 2→3→6→7 28，29，30，31，32 8，9，10 2 3→6→5 32，33，34，35，36 3，4，5，6，7 3 1→3→6→8 20，21，22，23 11，12，13，14，15 4 4→3→6→8 24，25，26，27，28 1，2 Attack signal Middle position between 1 - 3 34，35，36，37，38 None

[0089] It should be noted that the method of the embodiment of the present application can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In such a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiment of the present application, and these multiple devices will interact with each other to complete the described method.

[0090] It should be noted that some embodiments of the present application have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the above embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] Based on the same technical concept, corresponding to the method of any of the above embodiments, the present application further provides a classical quantum hybrid transmission network crosstalk attack positioning and mitigation device.

[0092] Reference Figure 7 , the classical quantum hybrid transmission network crosstalk attack positioning and mitigation device includes:

[0093] A supervised learning analysis module for crosstalk types corresponding to the transmission signals of the currently obtained classical quantum hybrid link;

[0094] An attack positioning module for constructing a positioning assistance graph corresponding to the crosstalk type according to the crosstalk type and determining the attack point and / or attack range of the crosstalk;

[0095] An attack mitigation module for constructing a rerouting topology of the transmission signal according to the priority of the transmission signal crosstalked by the crosstalk type, deleting the attack point and / or attack range of the crosstalk and adjusting the network traffic distribution.

[0096] For the convenience of description, when describing the above device, it is divided into various modules according to functions and described separately. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0097] The device of the above embodiment is used to implement the corresponding classical quantum hybrid transmission network crosstalk attack positioning and mitigation method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0098] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the classical quantum teleportation network crosstalk attack positioning and mitigation method described in any of the above embodiments is implemented.

[0099] Figure 8 FIG. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0100] The processor 1010 may be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present specification.

[0101] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of the present specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0102] The input / output interface 1030 is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0103] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module may implement communication in a wired manner (such as USB, network cable, etc.) or in a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0104] The bus 1050 includes a path for transmitting information between various components of the device, such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040.

[0105] It should be noted that although only the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050 are shown in the above device, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiment of the present specification, and does not necessarily include all the components shown in the figure.

[0106] The electronic device of the above embodiment is used to implement the corresponding classical quantum hybrid transmission network crosstalk attack positioning and mitigation method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0107] Based on the same technical concept, corresponding to the method of any of the above embodiments, the present application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the classical quantum hybrid transmission network crosstalk attack positioning and mitigation method as described in any of the above embodiments.

[0108] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0109] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the classical quantum hybrid transmission network crosstalk attack positioning and mitigation method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0110] Those of ordinary skill in the art should understand that any discussion of the above embodiments is merely exemplary and is not intended to imply that the scope of the present application (including the claims) is limited to these examples; under the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present application as described above, and for the sake of brevity, they are not provided in detail.

[0111] In addition, for simplicity of explanation and discussion, and in order not to make the embodiments of the present application difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application are to be implemented (i.e., these details should be entirely within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application may be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0112] Although the present application has been described in connection with specific embodiments of the present application, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0113] The embodiments of the present application are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present application shall be included within the protection scope of the present application.

Claims

1. A method for locating and mitigating crosstalk attacks in a classical quantum hybrid transmission network, characterized in that, Including: Input the transmission signal of the current classical quantum hybrid link into a pre-trained supervised learning model to obtain the crosstalk type corresponding to the crosstalk of the transmission signal by the attack signal; wherein, the current classical quantum hybrid link includes multiple wavelength channels, and the multiple wavelength channels are used to transmit the transmission signal; Based on the crosstalk type, construct a positioning assistance graph corresponding to the crosstalk type, and based on the positioning assistance graph, determine the wavelength channel where the attack point and / or attack range of the crosstalk is located, wherein the positioning assistance graph includes the path and node set through which the transmission signal affected by the crosstalk passes; Based on the priority of the transmission signal affected by the crosstalk type, construct a re-routing topology of the transmission signal and adjust the network traffic distribution, wherein the wavelength channel corresponding to the attack point and / or attack range of the crosstalk is deleted in the re-routing topology; The positioning assistance graph further includes: a first positioning assistance graph, a second positioning assistance graph, and a third positioning assistance graph; The constructing a positioning assistance graph corresponding to the crosstalk type based on the crosstalk type includes: Based on the crosstalk type being in-channel crosstalk, select the interrupted transmission signal affected by the in-channel crosstalk, and construct the first positioning assistance graph according to the path and wavelength channel division position passed by the head node and the tail node of the interrupted transmission signal; Based on the crosstalk type being inter-channel crosstalk, select the damaged transmission signal affected by the inter-channel crosstalk, and select adjacent wavelength channels on the overlapping path between the path passed by the damaged transmission signal and the path passed by the interrupted transmission signal to construct the second positioning assistance graph; Based on the crosstalk type being Raman scattering crosstalk, select the quantum signal affected by the Raman scattering crosstalk, and select the wavelength channel where the range of the attack signal wavelength on the overlapping path between the damaged transmission signal and the quantum signal affected by the Raman scattering crosstalk is located to construct the third positioning assistance graph; The determining the attack point and / or attack range of the crosstalk based on the positioning assistance graph includes: Compare the first positioning assistance graph with the third positioning assistance graph. If the wavelength channels on the overlapping path between the first positioning assistance graph and the third positioning assistance graph are the same, then the attack range is the link set where the tail node traffic of the overlapping path in the first positioning assistance graph is input; If the wavelength channels on the overlapping path between the first positioning assistance graph and the third positioning assistance graph are different, then the attack range of the attack signal is the link set where the head node traffic of the overlapping path in the first positioning assistance graph is input.

2. The method according to claim 1, characterized in that, The crosstalk type includes: in-channel crosstalk, inter-channel crosstalk, and Raman scattering crosstalk; The inputting the transmission signal of the current classical quantum hybrid link into a pre-trained supervised learning model to obtain the crosstalk type corresponding to the transmission signal includes: If the central wavelength of the wavelength channel where the attack signal is located is the same as or overlaps with the central wavelength of the wavelength channel where the transmission signal of the current classical quantum hybrid link is located, it is determined as in-channel crosstalk; The wavelength channel where the attack signal is located is adjacent to the central wavelength of the wavelength channel where the transmission signal of the current classical quantum hybrid link is located, which is determined as inter-channel crosstalk; The attack signal generates Raman scattering on the quantum signal in the transmission signal of the current classical quantum hybrid channel, which is determined as Raman scattering crosstalk.

3. The method according to claim 1, characterized in that, Based on the priority of the transmission signal affected by the crosstalk type, constructing a re-routing topology for the transmission signal and adjusting the network traffic distribution includes: Constructing a re-routing topology for the transmission signal with high priority affected by the crosstalk, where the wavelength channel where the attack point and / or attack range of the crosstalk is located is deleted in the re-routing topology; Adjusting the network traffic distribution, and adjusting the quantum signal in the transmission signal affected by the crosstalk to be carried on the wavelength channel with the farthest interval from the wavelength channel where the classical signal is located and the wavelength channel where the attack signal is located.

4. The method according to claim 1, characterized in that, The priority of the transmission signal affected by the crosstalk type is configured such that the interrupted transmission signal affected by the in-channel crosstalk takes precedence over the impaired transmission signal affected by the inter-channel crosstalk, which takes precedence over the quantum signal affected by Raman scattering crosstalk.

5. The method according to claim 1, characterized in that, The pre-trained supervised learning model is also used to output the relationship between the channel interval of the wavelength channel and the crosstalk value, for calculating the channel interval between the wavelength channel where the attack signal is located and the wavelength channel where the quantum signal is located; Based on the channel interval between the wavelength channel where the attack signal is located and the wavelength channel where the quantum signal is located, locating the attack signal.

6. A device for locating and mitigating crosstalk attacks in a classical quantum hybrid transmission network, characterized in that, Including: A supervised learning analysis module for analyzing the crosstalk type corresponding to the transmission signal of the current classical quantum hybrid link; An attack location module for constructing a positioning auxiliary graph corresponding to the crosstalk type according to the crosstalk type, and determining the attack point and / or attack range of the crosstalk; An attack mitigation module for constructing a re-routing topology for the transmission signal according to the priority of the transmission signal affected by the crosstalk type, deleting the attack point and / or attack range of the crosstalk and adjusting the network traffic distribution; The positioning auxiliary graph further includes: a first positioning auxiliary graph, a second positioning auxiliary graph, and a third positioning auxiliary graph; Constructing a positioning auxiliary graph corresponding to the crosstalk type according to the crosstalk type includes: Based on the crosstalk type being in-channel crosstalk, selecting the interrupted transmission signal affected by the in-channel crosstalk, and constructing the first positioning auxiliary graph according to the positions divided by the paths and wavelength channels passed by the head node and the tail node of the interrupted transmission signal; Based on the crosstalk type being inter-channel crosstalk, selecting the impaired transmission signal affected by the inter-channel crosstalk, and selecting the adjacent wavelength channels on the overlapping path between the path passed by the impaired transmission signal and the path passed by the interrupted transmission signal to construct the second positioning auxiliary graph; Based on the crosstalk type being Raman scattering crosstalk, selecting the quantum signal affected by the Raman scattering crosstalk, and selecting the wavelength channel where the range of the attack signal wavelength is located on the overlapping path between the impaired transmission signal and the quantum signal affected by the Raman scattering crosstalk to construct the third positioning auxiliary graph; Based on the positioning assistance graph, determining the attack point and / or attack range of the crosstalk, including: Comparing the first positioning assistance graph with the third positioning assistance graph, in response to the wavelength channels on the overlapping path between the first positioning assistance graph and the third positioning assistance graph being the same, the attack range is the link set where the traffic of the tail node of the overlapping path in the first positioning assistance graph is input; In response to the wavelength channels on the overlapping path between the first positioning assistance graph and the third positioning assistance graph being different, the attack range of the attack signal is the link set where the traffic of the head node of the overlapping path in the first positioning assistance graph is input.

7. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the program, it implements the method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 5.

Images