A multi-chain cross-chain verification defense method, system, and storage medium based on artificial intelligence

Abstract

This invention provides an AI-based multi-chain and cross-chain security verification method and system. By integrating machine learning technologies such as recurrent neural networks (RNNs) and graph neural networks (GNNs), a decentralized intelligent verification system is constructed. The method includes AI-driven cross-domain group authentication, distributed lightweight verification, dynamic credential generation, and threat knowledge graph analysis, enabling the detection of abnormal behavior in cross-chain interactions, dynamic threat warnings, and adaptive defense. The system does not rely on third-party institutions, can identify new attack patterns in real time, and dynamically adjust verification strategies, effectively improving security protection capabilities in multi-chain and cross-chain scenarios.

Description

Technical Field

[0001] This application relates to the field of cybersecurity technology, and in particular to a multi-chain and cross-chain security verification method and system based on artificial intelligence. Background Technology

[0002] Blockchain technology, with its decentralized, immutable, and fully traceable characteristics, provides a fundamental guarantee for transaction security. However, in cross-chain scenarios where multiple chains coexist independently, traditional identity verification mechanisms reveal significant flaws: reliance on third-party institutions such as key generation centers and certificate issuing authorities leads to single-point trust risks and fails to meet the inherent decentralized requirements of blockchain. Furthermore, with the abuse of artificial intelligence technology in cyberattacks (such as automated vulnerability scanning and intelligent spoofing attacks), cross-chain operations face more complex security threats, such as:

[0003] Insufficient dynamic threat identification: Traditional hash comparison and static certificate verification cannot detect new attack patterns generated by AI in real time (such as credential forgery based on GAN).

[0004] Cross-chain interconnection risks can get out of control: the lack of intelligent analysis of multi-chain interaction data makes it difficult to discover cross-chain vulnerability exploit chains (such as compound attacks that penetrate B chain through a vulnerability in chain A).

[0005] Rigid verification strategy: The fixed verification process cannot be dynamically adjusted according to the real-time threat level, resulting in insufficient verification strength in high-risk scenarios or waste of resources in low-risk scenarios.

[0006] Therefore, researching distributed cross-chain verification technology that integrates artificial intelligence to achieve intelligent perception, dynamic verification, and adaptive defense against cross-chain threats has become a key challenge in the current blockchain security field. There is an urgent need for a targeted AI-based multi-chain cross-chain security verification method and system. Summary of the Invention

[0007] The purpose of this invention is to provide a multi-chain and cross-chain security verification method and system based on artificial intelligence. By introducing machine learning, dynamic credential generation and threat knowledge graph technologies, a decentralized intelligent verification system is constructed.

[0008] Firstly, this application provides a multi-chain cross-chain security verification method based on artificial intelligence, the method comprising:

[0009] Train a cross-chain threat detection model using a recurrent neural network (RNN) or a graph neural network (GNN) to establish a behavioral baseline for normal interactions among group members;

[0010] Distributed lightweight verification is achieved by using the SHA-256 hash comparison algorithm, and the verification depth and breadth are dynamically adjusted by combining a reinforcement learning (RL) model.

[0011] The compliance of user identity verification is reviewed using a natural language processing (NLP) model, and risk characteristics are identified by analyzing certificate metadata using a convolutional neural network (CNN).

[0012] By generating dynamic signatures through generative adversarial networks (GANs), signed certificates are issued to users, and real-time detection of forged certificates is achieved by combining the isolated forest algorithm.

[0013] Construct a cross-chain threat knowledge graph, utilize graph neural networks (GNNs) to mine inter-chain related risks, and generate adaptive defense strategies.

[0014] Secondly, this application provides an artificial intelligence-based multi-chain cross-chain security verification system, the system comprising:

[0015] The data acquisition module is used to acquire cross-chain interaction data, group behavior characteristics, and chain state information;

[0016] The AI ​​modeling module is used to create cross-chain threat detection models;

[0017] The training module is used to train a cross-chain threat detection model using a recurrent neural network (RNN) or a graph neural network (GNN) to establish a baseline of normal interaction behavior among group members.

[0018] The dynamic verification module performs hash comparison, certificate metadata analysis, and dynamic signature verification. Specifically, it includes: implementing distributed lightweight verification using the SHA-256 hash comparison algorithm, dynamically adjusting the verification depth and breadth using a reinforcement learning (RL) model; verifying the compliance of user identity identifiers using a natural language processing (NLP) model, identifying risk characteristics by analyzing certificate metadata using a convolutional neural network (CNN); generating dynamic signatures using a generative adversarial network (GAN), issuing signed certificates to users, and achieving real-time detection of forged certificates using an isolated forest algorithm.

[0019] The threat analysis module is used to build a cross-chain threat knowledge graph, use graph neural networks (GNN) to mine risks associated with each chain, and output risk scores.

[0020] The strategy execution module is used to generate adaptive defense strategies and coordinate with multiple chain nodes to implement verification strategies and emergency responses.

[0021] Thirdly, this application provides an artificial intelligence-based multi-chain cross-chain security verification system, the system comprising a processor and a memory:

[0022] The memory is used to store program code and transmit the program code to the processor;

[0023] The processor is configured to execute any one of the methods described in the first aspect according to the instructions in the program code.

[0024] Fourthly, this application provides a computer-readable storage medium for storing program code, which is executed by a processor to implement the method described in any one of the first aspects.

[0025] Beneficial effects

[0026] This invention provides an AI-based multi-chain and cross-chain security verification method and system. By integrating machine learning technologies such as recurrent neural networks (RNNs) and graph neural networks (GNNs), a decentralized intelligent verification system is constructed. The method includes AI-driven cross-domain group authentication, distributed lightweight verification, dynamic credential generation, and threat knowledge graph analysis, enabling the detection of abnormal behavior in cross-chain interactions, dynamic threat warnings, and adaptive defense. The system does not rely on third-party institutions, can identify new attack patterns in real time, and dynamically adjust verification strategies, effectively improving security protection capabilities in multi-chain and cross-chain scenarios.

[0027] The method and system of the present invention have the following advantages and effects:

[0028] 1. Achieve fully decentralized cross-chain authentication without relying on trusted third parties.

[0029] 2. Build a certificate authentication system with independent authentication capabilities.

[0030] 3. Deeply integrate artificial intelligence technology into the verification process to achieve real-time analysis of user behavior, anomaly detection, and intelligent identification of potential network threats.

[0031] 4. Effectively resists complex attack modes such as group collusion attacks, and improves the overall security level in multi-chain and cross-chain environments.

[0032] 5. Optimize verification efficiency and reduce computational overhead in large-scale cross-chain scenarios. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of the present invention;

[0035] Figure 2 This is a system architecture diagram of the present invention. Detailed Implementation

[0036] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby providing a clearer and more explicit definition of the scope of protection of the present invention.

[0037] This application provides an AI-based multi-chain cross-chain security verification method, the method comprising:

[0038] Train a cross-chain threat detection model using a recurrent neural network (RNN) or a graph neural network (GNN) to establish a behavioral baseline for normal interactions among group members;

[0039] Distributed lightweight verification is achieved by using the SHA-256 hash comparison algorithm, and the verification depth and breadth are dynamically adjusted by combining a reinforcement learning (RL) model.

[0040] The compliance of user identity verification is reviewed using a natural language processing (NLP) model, and risk characteristics are identified by analyzing certificate metadata using a convolutional neural network (CNN).

[0041] By generating dynamic signatures through generative adversarial networks (GANs), signed certificates are issued to users, and real-time detection of forged certificates is achieved by combining the isolated forest algorithm.

[0042] Construct a cross-chain threat knowledge graph, utilize graph neural networks (GNNs) to mine inter-chain related risks, and generate adaptive defense strategies.

[0043] Specifically, a dynamic group is formed by cloud computing providers and users in the trusted domain. Data such as the behavioral characteristics (e.g., cross-chain frequency, access patterns) and asset attributes (e.g., chain type, node role) of the group members are collected. A cross-chain threat detection model is trained through recurrent neural networks (RNN) or graph neural networks (GNN) to establish a behavioral baseline for normal interaction.

[0044] Group members generate dynamic digital fingerprints (such as time-series hash values) containing behavioral characteristics for their respective clusters. Combining the immutability of blockchain, anomaly detection algorithms (such as isolated forests) are used to analyze the deviation of member behavior in real time and identify abnormal behaviors such as illegal cross-chain access and forged credentials.

[0045] Using the root node as the authentication center of the distributed system, the SHA-256 hash comparison algorithm is used to replace the traditional encryption and decryption process. By comparing the hash value of the user-submitted credentials with the system's stored value, fast verification is achieved, reducing computational complexity by more than 90%.

[0046] Introducing reinforcement learning (RL) models to dynamically adjust the depth and breadth of verification: In high-risk scenarios (such as cross-unknown chain interactions), the number of verification nodes is automatically increased, and multi-chain state synchronization verification is enabled; In low-risk scenarios, probability sampling verification is adopted to improve the efficiency of cross-chain transactions.

[0047] By analyzing certificate metadata (timestamps, cross-chain address entropy, etc.) through convolutional neural networks (CNNs), risk characteristics such as high-frequency abnormal requests and unfamiliar chain addresses are identified; generative adversarial networks (GANs) are used to verify the resistance to attacks of dynamic signatures, preventing replay attacks and credential forgery.

[0048] By integrating multi-chain vulnerability data (such as CVE numbers and exploitation difficulty), attack paths (such as cross-chain springboard attacks), and historical verification records, graph neural networks (GNNs) are used to mine inter-chain correlation risks and generate a cross-chain threat heatmap.

[0049] Based on the threat knowledge graph analysis results, the system automatically adjusts verification parameters (such as key update frequency and hash algorithm strength) and coordinates with multiple chains to perform defensive actions (such as isolating high-risk nodes and dynamically adjusting gas fee limits).

[0050] In some preferred embodiments, generating a dynamic signature and issuing a signed certificate to the user includes: the user generating a real identity identification code ID, generating a random public-private key pair (RAPK, RASK) using an elliptic curve cryptography algorithm (ECC), submitting the ID and public key RAPK to the key management center, the key management center reviewing the submission, generating an identifier private key IDSK using control information h and the private key RASK, and finally generating a dynamic certificate using a signature algorithm and sending the dynamic certificate to the user.

[0051] In some preferred embodiments, the real-time detection of forged certificates also includes an identifier-based certificate verification process, which includes: first, the user obtains a random number and adds the random number to the certificate, and generates an identifier-based dynamic signature; the user sends their dynamic verification to the verifier; the verifier determines the validity of the certificate through a triple verification mechanism of hash comparison, GAN signature verification, and identifier-based dynamic signature.

[0052] Users embed random numbers into credentials and generate dynamic signatures using a sequence-to-sequence (Seq2Seq) model. The signature changes dynamically with the random number during each verification, improving the credentials' resistance to interception.

[0053] Figure 2 The architecture diagram of the AI-based multi-chain cross-chain security verification system provided in this application is shown. The system includes:

[0054] The data acquisition module is used to acquire cross-chain interaction data, group behavior characteristics, and chain state information;

[0055] The AI ​​modeling module is used to create cross-chain threat detection models;

[0056] The training module is used to train a cross-chain threat detection model using a recurrent neural network (RNN) or a graph neural network (GNN) to establish a baseline of normal interaction behavior among group members.

[0057] The dynamic verification module performs hash comparison, certificate metadata analysis, and dynamic signature verification. Specifically, it includes: implementing distributed lightweight verification using the SHA-256 hash comparison algorithm, dynamically adjusting the verification depth and breadth using a reinforcement learning (RL) model; verifying the compliance of user identity identifiers using a natural language processing (NLP) model, identifying risk characteristics by analyzing certificate metadata using a convolutional neural network (CNN); generating dynamic signatures using a generative adversarial network (GAN), issuing signed certificates to users, and achieving real-time detection of forged certificates using an isolated forest algorithm.

[0058] The threat analysis module is used to build a cross-chain threat knowledge graph, use graph neural networks (GNN) to mine risks associated with each chain, and output risk scores.

[0059] The strategy execution module is used to generate adaptive defense strategies and coordinate with multiple chain nodes to implement verification strategies and emergency responses.

[0060] This application provides a multi-chain cross-chain security verification system based on artificial intelligence, the system comprising: a processor and a memory.

[0061] The memory is used to store program code and transmit the program code to the processor;

[0062] The processor is configured to execute the method described in any one of the embodiments of the first aspect according to the instructions in the program code.

[0063] This application provides a computer-readable storage medium for storing program code, which is executed by a processor to implement the method described in any one of the embodiments of the first aspect.

[0064] In a specific implementation, the present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and the program, when executed, may include some or all of the steps in the various embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0065] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present invention.

[0066] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0067] The embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention.

Claims

1. An artificial intelligence-based multi-chain cross-chain security verification method, characterized in that, The method comprises: A dynamic group is formed by a cloud computing provider in a trusted domain and a user, behavior characteristics and asset attributes of group members are collected, the behavior characteristics include cross-chain frequency and access mode, the asset attributes include chain type and node role, a cross-chain threat detection model is trained through a recurrent neural network (RNN) or a graph neural network (GNN), and a behavior baseline of normal interaction is established; Distributed lightweight verification is implemented by using a SHA-256 hash comparison algorithm, and the verification depth and breadth are dynamically adjusted by combining a reinforcement learning (RL) model, including: taking a root node as an authentication center of a distributed system, using a SHA-256 hash comparison algorithm, and realizing fast verification by comparing the hash value of a user-submitted credential with a system-stored value; for a high-risk scenario, the number of verification nodes is automatically increased, and multi-chain state synchronization verification is enabled; for a low-risk scenario, probabilistic sampling verification is used; A natural language processing (NLP) model is used to audit user identity compliance, and a convolutional neural network (CNN) is used to analyze certificate metadata to identify risk features; A generative adversarial network (GAN) is used to generate a dynamic signature, a signed certificate is issued to a user, and real-time detection of fake certificates is realized by combining an isolation forest algorithm; A cross-chain threat knowledge graph is constructed, a graph neural network (GNN) is used to mine inter-chain correlation risks, and an adaptive defense strategy is generated.

2. The method of claim 1, wherein: The generation of the dynamic signature and the issuance of the signed certificate to the user include: a user generates a real identity identification code (ID), generates a random public-private key pair (RAPK, RASK) through an elliptic curve encryption algorithm (ECC), submits the ID and the public key (RAPK) to a key management center, the key management center performs auditing, generates an identification private key (IDSK) from control information (h) and the private key (RASK), and finally generates a dynamic certificate through a signature algorithm and sends the dynamic certificate to the user.

3. The method of claim 1, wherein: The real-time detection of fake certificates also includes an identification-based certificate verification process, and the process includes: a user first obtains a random number, adds the random number to a certificate, and generates an identification-based dynamic signature; the user sends the dynamic verification to a verifier; and the verifier determines the validity of the certificate through a triple verification mechanism of hash comparison, GAN signature verification, and identification-based dynamic signature.

4. An artificial intelligence-based multi-chain cross-chain security verification system, characterized in that, The system comprises: A data collection module is configured to acquire cross-chain interaction data, group behavior characteristics, and chain state information; An AI modeling module is configured to create a cross-chain threat detection model; A training module is configured to form a dynamic group by a cloud computing provider in a trusted domain and a user, collect behavior characteristics and asset attributes of group members, the behavior characteristics include cross-chain frequency and access mode, the asset attributes include chain type and node role, train a cross-chain threat detection model through a recurrent neural network (RNN) or a graph neural network (GNN), and establish a behavior baseline of normal interaction. The dynamic verification module is used for performing hash comparison, certificate metadata analysis and dynamic signature verification, and specifically comprises: a distributed lightweight verification is realized by using a SHA-256 hash comparison algorithm, and a reinforcement learning (RL) model is combined to dynamically adjust the depth and breadth of verification, including: taking a root node as an authentication center of a distributed system, using a SHA-256 hash comparison algorithm, and realizing fast verification by comparing the hash value of a user-submitted certificate with a system-stored value; for a high-risk scenario, the number of verification nodes is automatically increased, and multi-chain state synchronization verification is enabled; for a low-risk scenario, probabilistic sampling verification is used; a natural language processing (NLP) model is used to audit user identity compliance, a convolutional neural network (CNN) is used to analyze certificate metadata to identify risk features; a generative adversarial network (GAN) is used to generate dynamic signatures, and a signed certificate is issued to a user, and an isolation forest algorithm is combined to realize real-time detection of fake certificates; The threat analysis module is used for constructing a cross-chain threat knowledge graph, using a graph neural network (GNN) to mine inter-chain correlation risks, and outputting risk scores; The strategy execution module is used for generating adaptive defense strategies, and implementing verification strategies and emergency responses in linkage with multi-chain nodes.

5. An artificial intelligence-based multi-chain cross-chain security verification system, characterized in that, The system comprises a processor and a memory: The memory is used for storing program code and transmitting the program code to the processor; The processor is used for executing instructions in the program code to realize the method of any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used for storing program code, and the program code is used for being executed by the processor to realize the method of any one of claims 1-3.

Images