Block chain data driven zero-knowledge proof intelligent security protection method and system

Abstract

The invention discloses a blockchain data-driven zero-knowledge proof intelligent security protection method and system, and belongs to the technical field of blockchains, and the key point of the technical scheme is that a layered architecture design is adopted, the system comprises a data layer, an analysis layer, a proof layer and a protection layer, and the layers cooperate to realize intelligent and adaptive blockchain security protection. According to the method, block chain data analysis and a zero-knowledge proof technology are organically combined, and automatic security policy execution is realized through the smart contract. The system firstly trains a protection model based on historical transaction data, and identifies an abnormal transaction mode; when a suspicious transaction is detected, a zero-knowledge proof verification mechanism is triggered, and a transaction initiator is required to provide a corresponding validity proof; meanwhile, the system can dynamically adjust security strategies and protection measures according to changes of attack modes, and the intelligent and self-adaptive security protection effect is achieved.

Description

Technical Field

[0001] This application relates to the field of blockchain technology, and more specifically to a blockchain data-driven zero-knowledge proof smart security protection method and system. Background Technology

[0002] Currently, blockchain security protection mainly adopts two types of technical solutions:

[0003] One approach is the traditional blockchain security monitoring solution, which involves deploying monitoring nodes to analyze on-chain data in real time, identify abnormal transactions and malicious behavior, and use preset rules for protection.

[0004] Second, a privacy protection scheme based on zero-knowledge proofs is used to ensure the legitimacy of transactions through cryptographic proofs, while protecting the privacy data of the transaction participants.

[0005] These solutions safeguard the security of blockchain systems from two dimensions: transaction monitoring and privacy protection. However, they have the following problems:

[0006] Traditional monitoring solutions rely on fixed rule bases, lack adaptive learning capabilities, and are difficult to cope with new attack methods;

[0007] Existing zero-knowledge proof schemes have high computational complexity, low verification efficiency, and focus only on privacy protection while neglecting overall security protection;

[0008] The two technologies are separate and do not effectively combine the advantages of data analysis and privacy protection;

[0009] The lack of an intelligent decision-making mechanism makes it impossible to dynamically adjust protection strategies based on the threat situation. Summary of the Invention

[0010] To address the shortcomings of existing technologies, the present invention aims to provide a blockchain data-driven zero-knowledge proof intelligent security protection method and system. Its advantage lies in the organic integration of blockchain data analysis and zero-knowledge proof technology, achieving automated execution of security policies through smart contracts. The system first trains a protection model based on historical transaction data to identify abnormal transaction patterns. When a suspicious transaction is detected, a zero-knowledge proof verification mechanism is triggered, requiring the transaction initiator to provide corresponding validity proof. Simultaneously, the system can dynamically adjust security strategies and protection measures according to changes in attack patterns, achieving intelligent and adaptive security protection.

[0011] To achieve the above objectives, this invention provides the following technical solution: a blockchain data-driven zero-knowledge proof intelligent security protection system, employing a layered architecture design, including a data layer, an analysis layer, a proof layer, and a protection layer, with each layer working together to achieve intelligent and adaptive blockchain security protection.

[0012] The data layer is used for the collection, storage, and preprocessing of blockchain data, and includes a blockchain data collection unit, a distributed storage unit, and a data preprocessing unit. The blockchain data collection unit collects transaction data, smart contract status data, and account behavior data in real time through the blockchain node API. The distributed storage unit uses sharding technology to store the collected data. The data preprocessing unit cleans, extracts features, and standardizes the collected data.

[0013] The analysis layer, used for security threat identification and risk assessment, includes a feature engineering module, a machine learning module, and an intelligent decision-making module. The feature engineering module constructs multi-dimensional feature vectors based on transaction pattern features, account behavior features, and time series features. The machine learning module uses an algorithm combining LSTM networks and random forests to build an anomaly detection model and updates the model parameters through an online learning mechanism. The intelligent decision-making module triggers corresponding protection strategies based on the risk assessment results output by the model.

[0014] The proof layer is used for the generation, verification, and management of zero-knowledge proofs, including a zero-knowledge proof generation unit, a proof verification module, and a proof management module. The zero-knowledge proof generation unit adopts the improved Groth16 protocol and generates zero-knowledge proofs through multi-threaded parallel processing. The proof verification module implements proof compression and batch verification. The proof management module supports the classified management of transaction validity proofs, asset ownership proofs, and identity authentication proofs.

[0015] The protection layer, used for the execution and optimization of security protection strategies, is deployed in smart contracts within the blockchain network and includes a strategy execution module, a protection optimization module, and a monitoring and feedback module. The strategy execution module executes transaction restrictions, account freezes, contract call interceptions, or emergency suspension operations based on risk assessment results. The protection optimization module dynamically adjusts the protection strategy according to changes in attack patterns. The monitoring and feedback module monitors system performance and protection effectiveness in real time.

[0016] In a further preferred embodiment of the present invention, the data collected by the blockchain data acquisition unit includes: transaction data such as transaction hash, sender address, receiver address, transaction amount, timestamp, and gas consumption; smart contract status data such as contract address, calling method, parameters, and execution status; and account behavior data such as account balance changes and interaction frequency.

[0017] A further preferred embodiment of the present invention includes the following implementation steps for the zero-knowledge proof generation unit: constructing an arithmetic circuit to represent the constraint relationship to be proved; using multi-threading technology to generate proofs in parallel; and optimizing the proof generation efficiency through pre-computation and witness compression technology.

[0018] A further preferred embodiment of the present invention is that the smart contract of the protection layer ensures the consistency of the execution of protection strategies by each node in the network through a consensus mechanism, and supports dynamic updates of protection strategies and emergency response mechanisms.

[0019] A further preferred embodiment of the present invention includes a deployment layer that employs containerization technology to enable rapid system deployment and elastic scaling, uses configuration management tools to achieve unified management of system parameters, and provides log recording and auditing functions.

[0020] A blockchain data-driven zero-knowledge proof smart security protection method includes the following steps:

[0021] S1. Data Acquisition and Preprocessing: Real-time acquisition of blockchain transaction data, smart contract status data, and account behavior data through the data layer. After cleaning, feature extraction, and standardization, the data is stored in a distributed storage unit.

[0022] S2, Intelligent Analysis and Risk Assessment: The feature engineering module of the analysis layer constructs multi-dimensional feature vectors, the machine learning module captures time-series features through the LSTM network, and identifies abnormal transaction patterns by combining the random forest algorithm, and the intelligent decision-making module outputs risk assessment results;

[0023] S3. Zero-knowledge proof generation and verification: If the risk assessment result is a suspicious transaction, the zero-knowledge proof generation unit of the proof layer is triggered, and a zero-knowledge proof is generated using the improved Groth16 protocol. The proof verification module verifies the validity of the proof through a batch verification mechanism.

[0024] S4. Smart Protection Strategy Execution: The strategy execution module of the protection layer executes the corresponding protection operations through smart contracts based on the risk assessment results and proof verification results; transactions that pass verification and have low risk are executed normally, while transactions that fail verification or have high risk are blocked.

[0025] S5. Protection Strategy Optimization: The monitoring and feedback module collects system performance and protection effectiveness data in real time, and the protection optimization module dynamically adjusts the protection strategy and anomaly detection model parameters based on the data to achieve adaptive protection.

[0026] A further preferred embodiment of the present invention is that the online learning mechanism of the machine learning module in step 2 includes: periodically collecting new blockchain data, incrementally training the anomaly detection model, and updating the model parameters to adapt to new attack patterns.

[0027] A further preferred embodiment of the present invention is that the verification of the zero-knowledge proof in step 3 supports the participation of third parties, who can verify the legality of the transaction without knowing the specific transaction content.

[0028] A further preferred embodiment of the present invention includes the following protective operations in step 4: dynamically adjusting transaction restrictions, temporarily freezing suspicious accounts, intercepting abnormal contract calls, and triggering an emergency pause mechanism.

[0029] A further preferred embodiment of the present invention includes: the protection strategy optimization in step 5 further includes: adjusting the number of parallel threads for proof generation and the pre-computation parameters based on the generation efficiency and verification success rate of zero-knowledge proofs.

[0030] In summary, the present invention has the following advantages:

[0031] This system collects real-time transaction data, smart contract execution status, and account behavior characteristics from the blockchain, and combines this with machine learning algorithms to build a security threat identification model, providing early warnings and protection against potential security risks. Based on data analysis, the system generates zero-knowledge proofs for each sensitive operation, ensuring the legality and privacy of transactions, while also supporting third-party verification of transactions without needing to know the specific transaction content.

[0032] The core of this system lies in the organic integration of blockchain data analysis with zero-knowledge proof technology, enabling automated execution of security policies through smart contracts. The system first trains a protection model based on historical transaction data to identify abnormal transaction patterns. When a suspicious transaction is detected, a zero-knowledge proof verification mechanism is triggered, requiring the transaction initiator to provide corresponding proof of validity. Simultaneously, the system can dynamically adjust security policies and protective measures according to changes in attack patterns, achieving intelligent and adaptive security protection. Attached Figure Description

[0033] Figure 1 This is a system architecture diagram of the present invention;

[0034] Figure 2 This is a flowchart of the present invention. Detailed Implementation

[0035] The present invention will be further described in detail below with reference to the accompanying drawings.

[0036] like Figure 1 As shown, a blockchain data-driven zero-knowledge proof intelligent security protection system adopts a layered architecture design, including a data layer, an analysis layer, a proof layer, and a protection layer. Each layer works together to achieve intelligent and adaptive blockchain security protection.

[0037] The data layer is used for the collection, storage, and preprocessing of blockchain data, including a blockchain data collection unit, a distributed storage unit, and a data preprocessing unit. The blockchain data collection unit collects transaction data, smart contract status data, and account behavior data in real time through the blockchain node API. The distributed storage unit uses sharding technology to store the collected data. The data preprocessing unit cleans, extracts features, and standardizes the collected data.

[0038] The analysis layer, used for security threat identification and risk assessment, includes a feature engineering module, a machine learning module, and an intelligent decision-making module. The feature engineering module constructs multi-dimensional feature vectors based on transaction pattern features, account behavior features, and time series features. The machine learning module uses an algorithm combining LSTM networks and random forests to build an anomaly detection model and updates the model parameters through an online learning mechanism. The intelligent decision-making module triggers corresponding protection strategies based on the risk assessment results output by the model.

[0039] The proof layer is used for the generation, verification, and management of zero-knowledge proofs. It includes a zero-knowledge proof generation unit, a proof verification module, and a proof management module. The zero-knowledge proof generation unit adopts the improved Groth16 protocol and generates zero-knowledge proofs through multi-threaded parallel processing. The proof verification module implements proof compression and batch verification. The proof management module supports the classified management of transaction validity proofs, asset ownership proofs, and identity authentication proofs.

[0040] The protection layer, used for the execution and optimization of security protection strategies, is deployed in smart contracts on the blockchain network and includes a strategy execution module, a protection optimization module, and a monitoring and feedback module. The strategy execution module executes transaction restrictions, account freezes, contract call interception, or emergency suspension operations based on risk assessment results. The protection optimization module dynamically adjusts the protection strategy according to changes in attack patterns. The monitoring and feedback module monitors system performance and protection effectiveness in real time.

[0041] Preferably, the data collected by the blockchain data collection unit includes: transaction data such as transaction hash, sender address, receiver address, transaction amount, timestamp, and gas consumption; smart contract status data such as contract address, calling method, parameters, and execution status; and account behavior data such as account balance changes and interaction frequency.

[0042] Preferably, the implementation steps of the zero-knowledge proof generation unit include: constructing an arithmetic circuit to represent the constraint relationship to be proved; using multi-threading technology to generate proofs in parallel; and optimizing the proof generation efficiency through pre-computation and witness compression technology.

[0043] Preferably, the smart contract of the protection layer ensures the consistency of protection strategy execution among network nodes through a consensus mechanism, and supports dynamic updates of protection strategies and emergency response mechanisms.

[0044] Preferably, it also includes a deployment layer, which uses containerization technology to enable rapid system deployment and elastic scaling, uses configuration management tools to achieve unified management of system parameters, and provides logging and auditing functions.

[0045] like Figure 2 As shown, a blockchain data-driven zero-knowledge proof smart security protection method includes the following steps:

[0046] S1. Data Acquisition and Preprocessing: Real-time acquisition of blockchain transaction data, smart contract status data, and account behavior data through the data layer. After cleaning, feature extraction, and standardization, the data is stored in a distributed storage unit.

[0047] S2, Intelligent Analysis and Risk Assessment: The feature engineering module of the analysis layer constructs multi-dimensional feature vectors, the machine learning module captures time-series features through the LSTM network, and identifies abnormal transaction patterns by combining the random forest algorithm, and the intelligent decision-making module outputs risk assessment results;

[0048] S3. Zero-knowledge proof generation and verification: If the risk assessment result is a suspicious transaction, the zero-knowledge proof generation unit of the proof layer is triggered, and a zero-knowledge proof is generated using the improved Groth16 protocol. The proof verification module verifies the validity of the proof through a batch verification mechanism.

[0049] S4. Smart Protection Strategy Execution: The strategy execution module of the protection layer executes the corresponding protection operations through smart contracts based on the risk assessment results and proof verification results; transactions that pass verification and have low risk are executed normally, while transactions that fail verification or have high risk are blocked.

[0050] S5. Protection Strategy Optimization: The monitoring and feedback module collects system performance and protection effectiveness data in real time, and the protection optimization module dynamically adjusts the protection strategy and anomaly detection model parameters based on the data to achieve adaptive protection.

[0051] Preferably, the online learning mechanism of the machine learning module in step 2 includes: periodically collecting new blockchain data, incrementally training the anomaly detection model, and updating the model parameters to adapt to new attack patterns.

[0052] Preferably, the zero-knowledge proof verification in step 3 supports third-party participation, allowing the third party to verify the legality of the transaction without needing to know the specific transaction content.

[0053] Preferably, the protective operations in step 4 include: dynamically adjusting transaction restrictions, temporarily freezing suspicious accounts, intercepting abnormal contract calls, and triggering an emergency pause mechanism.

[0054] Preferably, the protection strategy optimization in step 5 also includes: adjusting the number of parallel threads for proof generation and the pre-computation parameters based on the generation efficiency and verification success rate of zero-knowledge proofs.

[0055] The working process and beneficial effects of this invention are as follows:

[0056] From a technical perspective, this invention achieves an intelligent security protection mechanism by integrating blockchain data analysis and zero-knowledge proof technology. The system demonstrates significant performance advantages in actual testing, including improved proof verification speed, reduced system response time, and lower resource consumption. Simultaneously, through real-time analysis and dynamic optimization of machine learning models, the system improves the accuracy of anomaly detection, reduces false alarm rates, and significantly enhances the precision and efficiency of security protection.

[0057] In practical application, this invention significantly improves the security and availability of blockchain systems. In blockchain networks where this system is deployed, the incidence of security incidents has decreased markedly, successfully preventing various types of attacks, including replay attacks, smart contract vulnerability exploitation, and account manipulation. Simultaneously, due to the adoption of an adaptive protection mechanism, the system reduces operational costs, decreases the volume of suspicious transactions, and improves the security operation efficiency of the blockchain network. Furthermore, the application of zero-knowledge proof technology ensures that while providing security protection, it also effectively protects the privacy data of transaction participants.

[0058] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the design concept of the present invention should be included within the protection scope of the present invention.

Claims

1. A blockchain data-driven zero-knowledge proof intelligent security protection system, characterized in that, It adopts a layered architecture design, including a data layer, an analysis layer, a proof layer, and a protection layer. Each layer works together to achieve intelligent and adaptive blockchain security protection. The data layer is used for the collection, storage, and preprocessing of blockchain data, including a blockchain data collection unit, a distributed storage unit, and a data preprocessing unit. The blockchain data acquisition unit collects transaction data, smart contract status data, and account behavior data in real time through the blockchain node API; the distributed storage unit uses sharding technology to store the collected data. The data preprocessing unit cleans, extracts features, and standardizes the collected data. The analysis layer, used for security threat identification and risk assessment, includes a feature engineering module, a machine learning module, and an intelligent decision-making module; the feature engineering module constructs multi-dimensional feature vectors of transaction pattern features, account behavior features, and time series features; The machine learning module uses an algorithm combining LSTM network and random forest to build an anomaly detection model and updates the model parameters through an online learning mechanism; the intelligent decision-making module triggers corresponding protection strategies based on the risk assessment results output by the model. The proof layer is used for the generation, verification, and management of zero-knowledge proofs, and includes a zero-knowledge proof generation unit, a proof verification module, and a proof management module. The zero-knowledge proof generation unit adopts the improved Groth16 protocol and generates zero-knowledge proofs through multi-threaded parallel processing; the proof verification module implements proof compression and batch verification. The proof management module supports the categorized management of transaction validity proofs, asset ownership proofs, and identity authentication proofs; The protection layer, used for the execution and optimization of security protection strategies, is deployed in smart contracts within the blockchain network and includes a strategy execution module, a protection optimization module, and a monitoring and feedback module. The strategy execution module executes transaction restrictions, account freezes, contract call interceptions, or emergency suspension operations based on risk assessment results. The protection optimization module dynamically adjusts the protection strategy according to changes in attack patterns. The monitoring and feedback module monitors system performance and protection effectiveness in real time.

2. The blockchain data-driven zero-knowledge proof intelligent security protection system according to claim 1, characterized in that, The data collected by the blockchain data acquisition unit includes: transaction data such as transaction hash, sender address, receiver address, transaction amount, timestamp, and gas consumption; smart contract status data such as contract address, calling method, parameters, and execution status; and account behavior data such as account balance changes and interaction frequency.

3. The blockchain data-driven zero-knowledge proof intelligent security protection system according to claim 1, characterized in that, The implementation steps of the zero-knowledge proof generation unit include: constructing an arithmetic circuit to represent the constraint relationship to be proved; using multi-threading technology to generate proofs in parallel; and optimizing the proof generation efficiency through pre-computation and witness compression technology.

4. The blockchain data-driven zero-knowledge proof intelligent security protection system according to claim 1, characterized in that, The smart contracts of the protection layer ensure the consistency of protection strategy execution across network nodes through a consensus mechanism, and support dynamic updates of protection strategies and emergency response mechanisms.

5. A blockchain data-driven zero-knowledge proof intelligent security protection system according to claim 1, characterized in that, It also includes a deployment layer, which uses containerization technology to enable rapid system deployment and elastic scaling, uses configuration management tools to achieve unified management of system parameters, and provides logging and auditing functions.

6. A blockchain data-driven zero-knowledge proof intelligent security protection method, characterized in that, Applying the system according to any one of claims 1-5 includes the following steps: S1. Data Acquisition and Preprocessing: Real-time acquisition of blockchain transaction data, smart contract status data, and account behavior data through the data layer. After cleaning, feature extraction, and standardization, the data is stored in a distributed storage unit. S2, Intelligent Analysis and Risk Assessment: The feature engineering module of the analysis layer constructs multi-dimensional feature vectors, the machine learning module captures time-series features through the LSTM network, and identifies abnormal transaction patterns by combining the random forest algorithm, and the intelligent decision-making module outputs risk assessment results; S3. Zero-knowledge proof generation and verification: If the risk assessment result is a suspicious transaction, the zero-knowledge proof generation unit of the proof layer is triggered, and a zero-knowledge proof is generated using the improved Groth16 protocol. The proof verification module verifies the validity of the proof through a batch verification mechanism. S4. Smart Protection Strategy Execution: The strategy execution module of the protection layer executes the corresponding protection operations through smart contracts based on the risk assessment results and proof verification results; transactions that pass verification and have low risk are executed normally, while transactions that fail verification or have high risk are blocked. S5. Protection Strategy Optimization: The monitoring and feedback module collects system performance and protection effectiveness data in real time, and the protection optimization module dynamically adjusts the protection strategy and anomaly detection model parameters based on the data to achieve adaptive protection.

7. A blockchain data-driven zero-knowledge proof intelligent security protection method according to claim 6, characterized in that, The online learning mechanism of the machine learning module mentioned in step S2 includes: periodically collecting new blockchain data, incrementally training the anomaly detection model, and updating the model parameters to adapt to new attack patterns.

8. A blockchain data-driven zero-knowledge proof intelligent security protection method according to claim 6, characterized in that, The zero-knowledge proof verification described in step S3 supports third-party participation, allowing third parties to verify the legality of a transaction without needing to know the specific transaction content.

9. A blockchain data-driven zero-knowledge proof intelligent security protection method according to claim 6, characterized in that, The protective operations described in step S4 include: dynamically adjusting transaction restrictions, temporarily freezing suspicious accounts, intercepting abnormal contract calls, and triggering an emergency pause mechanism.

10. The blockchain data-driven zero-knowledge proof intelligent security protection method according to claim 6, characterized in that, The protection strategy optimization described in step S5 also includes: adjusting the number of parallel threads for proof generation and the pre-computation parameters based on the generation efficiency and verification success rate of zero-knowledge proofs.

Images