An AI-based method for cybersecurity data analysis

Abstract

This invention belongs to the field of network security technology and discloses an artificial intelligence-based network security data analysis method. This invention provides an analysis method for network data security during cross-platform data collaboration. First, it extracts characteristic parameters of authentication, data encryption, and access transmission during the cross-platform data collaboration process, and performs dimensionless processing on these characteristic parameters to unify different parameters onto the same scale. Based on the security characteristic parameters of authentication, data encryption, and access transmission, it calculates the corresponding security coefficients. Based on different security coefficients, it evaluates the security of the current stage of cross-platform data collaboration and predicts the security of the next stage of cross-platform data collaboration based on the current evaluation results. Through multi-dimensional data analysis, it accurately identifies network data security risks, improving the accuracy and comprehensiveness of security detection.

Description

Technical Field

[0001] This invention belongs to the field of network security technology, specifically relating to a network security data analysis method based on artificial intelligence. Background Technology

[0002] With the rapid development of information technology, cybersecurity issues are becoming increasingly serious. Cyberattack methods are constantly evolving, posing a significant threat to the information security of individuals, businesses, and even nations. Traditional cybersecurity protection methods primarily rely on comparing network characteristic parameters with thresholds to analyze cybersecurity data.

[0003] However, with the rapid development of information technology, cross-platform data collaboration has become increasingly common in organizations such as enterprises and research institutions. Data interaction and sharing between different platforms greatly improves work efficiency and resource utilization. However, due to differences in platform architecture, security policies, and data formats, data is vulnerable to attacks during transmission and storage. Existing network security measures often cannot comprehensively and accurately address the complex security issues arising from cross-platform data collaboration. Therefore, developing an analytical method for network security data during cross-platform data collaboration is of significant practical importance. Summary of the Invention

[0004] The purpose of this invention is to provide an artificial intelligence-based network security data analysis method to solve the problems faced in the background art.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A cybersecurity data analysis method based on artificial intelligence, the method comprising the following steps:

[0007] Step S1: Collect cross-platform data collaboration data packets using a network traffic collection device;

[0008] Step S2: Extract the feature parameters from the data packet, and process all feature parameters based on artificial intelligence to unify different parameters to the same scale;

[0009] Step S3: Analyze the feature parameters and assess the security of cross-platform data collaboration at the current stage based on the analysis results;

[0010] Step S4: Based on the analysis results, predict the security of cross-platform data collaboration in the next stage.

[0011] As a further description of the technical solution of the present invention, the specific working process of step S2 includes:

[0012] The feature parameters include: authentication parameters, data encryption parameters, and access transmission parameters;

[0013] The authentication parameters include: password complexity parameters and multi-factor authentication parameters;

[0014] The data encryption parameters include: encryption algorithm parameters and key management parameters;

[0015] The access transmission parameters include: transmission protocol parameters and data integrity verification parameters.

[0016] As a further description of the technical solution of the present invention, the specific working process of step S3 includes:

[0017] Step S31: Obtain the authentication, data encryption, and access transmission security coefficients respectively;

[0018] Step S32: Obtain the cross-platform data collaboration security factor based on authentication, data encryption, and access transmission security factor;

[0019] Step S33: Compare the authentication, data encryption, and access transmission security coefficients with the system-set authentication, data encryption, and access transmission security coefficient thresholds respectively. If any security coefficient is greater than or equal to the system-set security coefficient threshold, it indicates that the cross-platform data collaboration security is unqualified. If no security coefficient is greater than or equal to the system-set security coefficient threshold, proceed to step S34.

[0020] Step S34: Compare the cross-platform data collaboration security coefficient with the cross-platform data collaboration security coefficient threshold set by the system. If the cross-platform data collaboration security coefficient is greater than or equal to the cross-platform data collaboration security coefficient threshold set by the system, it indicates that there is a potential risk to the cross-platform data collaboration security.

[0021] As a further description of the technical solution of the present invention, the process of obtaining the authentication security coefficient in step S31 includes:

[0022] Obtain the authentication parameters, and construct an authentication security coefficient calculation model based on the authentication parameters. The expression is:

[0023] ;

[0024] In the formula, For authentication security level, This is a coefficient representing the cryptographic complexity index. For the verification code index coefficient, and These are the weighting coefficients corresponding to the password complexity index coefficient and the verification code index coefficient, respectively.

[0025] As a further description of the technical solution of the present invention, the process of obtaining the data encryption security coefficient in step S31 includes:

[0026] Obtain the data encryption parameters, and construct a data encryption security coefficient calculation model based on the data encryption parameters. The expression is:

[0027] ;

[0028] In the formula, To enhance data encryption security, For encryption algorithm index coefficients, This is a key management indicator coefficient. and These are the weighting coefficients corresponding to the encryption algorithm index coefficient and the key management index coefficient, respectively.

[0029] As a further description of the technical solution of the present invention, the working process of obtaining the access transmission security factor in step S31 includes:

[0030] Obtain the access transmission parameters, and construct an access transmission security factor calculation model based on the access transmission parameters. The expression is:

[0031] ;

[0032] In the formula, To ensure the security of access transmission, For transmission protocol index coefficients, The coefficient for data integrity verification index. and and are the weighting coefficients corresponding to the transmission protocol index coefficient and the data integrity verification index coefficient, respectively.

[0033] As a further description of the technical solution of the present invention, the method for obtaining the cross-platform data collaboration security coefficient in step S32 includes:

[0034] Construct a cross-platform data collaboration security factor calculation model, with the following expression:

[0035] ;

[0036] In the formula, , and These are the weighting coefficients corresponding to the authentication security coefficient, data encryption security coefficient, and transmission security coefficient, respectively.

[0037] As a further description of the technical solution of the present invention, the working process of step S4 includes:

[0038] Obtain the current authentication parameters, data encryption parameters, and access transmission parameters, substitute them into the cross-platform data collaboration security coefficient calculation model, and obtain the current cross-platform data collaboration security coefficient. To construct the next stage cross-platform data collaboration security coefficient calculation model, the expression is:

[0039] ;

[0040] In the formula, After normalization, the value range is from 0 to 1. The security factor for cross-platform data collaboration in the next stage will range from 0 to 1. To account for the impact of unforeseen factors, W=0 when there are no unforeseen factors, W=1 when there are unforeseen factors with a positive impact, and W=-1 when there are unforeseen factors with a negative impact. This is the self-regulation coefficient; the stronger the self-regulation ability, the better. The larger;

[0041] The next stage of cross-platform data collaboration security factor is input into the trained artificial intelligence model to predict the next stage of cross-platform data collaboration security level.

[0042] The beneficial effects of this invention are:

[0043] 1. This invention provides an analysis method for network data security during cross-platform data collaboration. First, it extracts characteristic parameters of authentication, data encryption, and access transmission during the cross-platform data collaboration process, and performs dimensionless processing on these characteristic parameters to unify different parameters onto the same scale. Based on the security characteristic parameters of authentication, data encryption, and access transmission, it calculates the corresponding security coefficients. Based on different security coefficients, it evaluates the security system of the current stage of cross-platform data collaboration and predicts the security of the next stage of cross-platform data collaboration based on the current evaluation results. Through multi-dimensional data analysis, it accurately identifies network data security risks and improves the accuracy and comprehensiveness of security detection.

[0044] 2. Based on the risk assessment results of cross-platform data collaboration at the current stage and combined with environmental factors, the risk of cross-platform data collaboration in the next stage can be predicted, which can quickly adapt to the ever-changing cross-platform attack patterns and promptly detect new security threats.

[0045] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a partial flowchart of the AI-based network security data analysis method of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] Please see Figure 1 As shown, a cybersecurity data analysis method based on artificial intelligence is disclosed, the method comprising the following steps:

[0050] Step S1: Collect cross-platform data collaboration data packets using a network traffic collection device;

[0051] Step S2: Extract the feature parameters from the data packet, and process all feature parameters based on artificial intelligence to unify different parameters to the same scale;

[0052] Step S3: Analyze the feature parameters and assess the security of cross-platform data collaboration at the current stage based on the analysis results;

[0053] Step S4: Based on the analysis results, predict the security of cross-platform data collaboration in the next stage.

[0054] Through the above technical solution, this invention provides an analysis method for network data security during cross-platform data collaboration. First, it extracts characteristic parameters related to authentication, data encryption, and access transmission during the cross-platform data collaboration process. These characteristic parameters are then processed without dimensions, unifying different parameters to the same scale. Based on the security characteristic parameters of authentication, data encryption, and access transmission, corresponding security coefficients are calculated. Based on these different security coefficients, the security system of the current stage of cross-platform data collaboration is evaluated. Based on the current evaluation results, the security of the next stage of cross-platform data collaboration is predicted. Through multi-dimensional data analysis, network data security risks are accurately identified, improving the accuracy and comprehensiveness of security detection.

[0055] As a further description of the technical solution of the present invention, the specific working process of step S2 includes:

[0056] The feature parameters include: authentication parameters, data encryption parameters, and access transmission parameters;

[0057] The authentication parameters include: password complexity parameters and multi-factor authentication parameters;

[0058] The data encryption parameters include: encryption algorithm parameters and key management parameters;

[0059] The access transmission parameters include: transmission protocol parameters and data integrity verification parameters.

[0060] As a further description of the technical solution of the present invention, the specific working process of step S3 includes:

[0061] Step S31: Obtain the authentication, data encryption, and access transmission security coefficients respectively;

[0062] Step S32: Obtain the cross-platform data collaboration security factor based on authentication, data encryption, and access transmission security factor;

[0063] Step S33: Compare the authentication, data encryption, and access transmission security coefficients with the system-set authentication, data encryption, and access transmission security coefficient thresholds respectively. If any security coefficient is greater than or equal to the system-set security coefficient threshold, it indicates that the cross-platform data collaboration security is unqualified. If no security coefficient is greater than or equal to the system-set security coefficient threshold, proceed to step S34.

[0064] Step S34: Compare the cross-platform data collaboration security coefficient with the cross-platform data collaboration security coefficient threshold set by the system. If the cross-platform data collaboration security coefficient is greater than or equal to the cross-platform data collaboration security coefficient threshold set by the system, it indicates that there is a potential risk to the cross-platform data collaboration security.

[0065] As a further description of the technical solution of the present invention, the process of obtaining the authentication security coefficient in step S31 includes:

[0066] Obtain the authentication parameters, and construct an authentication security coefficient calculation model based on the authentication parameters. The expression is:

[0067] ;

[0068] In the formula, For authentication security level, This is a coefficient representing the cryptographic complexity index. For the verification code index coefficient, and These are the weighting coefficients corresponding to the password complexity index coefficient and the verification code index coefficient, respectively.

[0069] The method for obtaining the cryptographic complexity index coefficient includes:

[0070] Get password length Get the minimum password length requirement set by the system. and maximum expected length ;

[0071] Get password character type Obtain the minimum character requirement for the password set by the system. and maximum expected character type ;

[0072] Construct a model for calculating the cryptographic complexity index coefficient, with the following expression:

[0073] ;

[0074] The method for obtaining the verification code index coefficient includes:

[0075] Number of retries for obtaining verification code if error occurs R Get the system-defined range of error retries. ;

[0076] Get the verification code verification duration T, and get the verification code verification duration range set by the system. ;

[0077] Construct a model for calculating the CAPTCHA index coefficients, with the following expression:

[0078] .

[0079] As a further description of the technical solution of the present invention, the process of obtaining the data encryption security coefficient in step S31 includes:

[0080] Obtain the data encryption parameters, and construct a data encryption security coefficient calculation model based on the data encryption parameters. The expression is:

[0081] ;

[0082] In the formula, To enhance data encryption security, For encryption algorithm index coefficients, This is a key management indicator coefficient. and These are the weighting coefficients corresponding to the encryption algorithm index coefficient and the key management index coefficient, respectively.

[0083] The method for obtaining the index coefficients of the encryption algorithm includes:

[0084] The key length is K bits. Values ​​are assigned to the coefficients of the encryption algorithm based on the key length. When k=128... When k=192, When k=256, ;

[0085] The method for obtaining the key management index coefficients includes:

[0086] The seed length for obtaining random numbers is Obtain the random number seed length range set by the system. ;

[0087] The validity period for obtaining the key distribution is Obtain the key distribution validity period set by the system. ;

[0088] Construct a key management index coefficient calculation model, the expression of which is:

[0089] .

[0090] As a further description of the technical solution of the present invention, the working process of obtaining the access transmission security factor in step S31 includes:

[0091] Obtain the access transmission parameters, and construct an access transmission security factor calculation model based on the access transmission parameters. The expression is:

[0092] ;

[0093] In the formula, To ensure the security of access transmission, For transmission protocol index coefficients, The coefficient for data integrity verification index. and and are the weighting coefficients corresponding to the transmission protocol index coefficient and the data integrity verification index coefficient, respectively;

[0094] The method for obtaining the transmission protocol index coefficients includes:

[0095] The validity period of the obtained agreement certificate is Obtain the key distribution validity period set by the system. ;

[0096] Based on actual survey results, a trust level is assigned to the protocol. When the trust rate exceeds 80%, the trust level is [not specified]. When the trust rate does not exceed 80%, the trust level is... ;

[0097] Construct a model for calculating transmission protocol index coefficients, with the following expression:

[0098] ;

[0099] The method for obtaining the data integrity verification index coefficient includes:

[0100] The fault tolerance parameter for obtaining hash value comparison is: Obtain the system-defined hash value and compare it with the fault tolerance parameter range. ;

[0101] ;

[0102] In the formula, This is the hash value algorithm index coefficient, which is assigned a value according to the hash value algorithm used by the transmission protocol.

[0103] Through the above technical solution, this embodiment provides a risk assessment method for cross-platform data collaboration. First, it obtains the password length. Get the minimum password length requirement set by the system. and maximum expected length Password character type Obtain the minimum character requirement for the password set by the system. and maximum expected character type The password complexity index coefficient is calculated based on the obtained parameters, and the number of retries for incorrect verification codes is obtained. R Get the system-defined range of error retries. Get the verification code verification duration T, and get the verification code verification duration range set by the system. The verification code index coefficient is calculated based on the obtained parameters. The password complexity index coefficient and the verification code index coefficient are then weighted and summed to obtain the identity verification security coefficient. Next, the key length is obtained, and the encryption algorithm index coefficient is assigned a value based on this key length. The random number seed length is then determined. Obtain the random number seed length range set by the system. The validity period for obtaining the key distribution is Obtain the key distribution validity period set by the system. Based on the acquired parameters, the key management index coefficient is calculated. The encryption security coefficient is obtained by weighted summation of the encryption algorithm index coefficient and the key management index coefficient. Then, based on the actual survey results, a trust level is assigned to the protocol, and the validity period of the protocol certificate is determined. Obtain the key distribution validity period set by the system. Based on the assignment results and the obtained parameters, the transmission protocol index coefficients are calculated, and the hash value comparison fault tolerance parameter is obtained. Obtain the system-defined hash value and compare it with the fault tolerance parameter range. The hash value algorithm index coefficient is assigned according to the hash value algorithm used by the transmission protocol. The data integrity verification index coefficient is calculated based on the obtained parameters and the assignment results. The access transmission security coefficient is obtained by weighted summation of the transmission protocol index coefficient and the data integrity verification index coefficient.

[0104] As a further description of the technical solution of the present invention, the method for obtaining the cross-platform data collaboration security coefficient in step S32 includes:

[0105] Construct a cross-platform data collaboration security factor calculation model, with the following expression:

[0106] ;

[0107] In the formula, , and These are the weighting coefficients corresponding to the authentication security coefficient, data encryption security coefficient, and transmission security coefficient, respectively.

[0108] As a further description of the technical solution of the present invention, the working process of step S4 includes:

[0109] Obtain the current authentication parameters, data encryption parameters, and access transmission parameters, substitute them into the cross-platform data collaboration security coefficient calculation model, and obtain the current cross-platform data collaboration security coefficient. To construct the next stage cross-platform data collaboration security coefficient calculation model, the expression is:

[0110] ;

[0111] In the formula, After normalization, the value range is from 0 to 1. The security factor for cross-platform data collaboration in the next stage will range from 0 to 1. To account for the impact of unforeseen factors, W=0 when there are no unforeseen factors, W=1 when there are unforeseen factors with a positive impact, and W=-1 when there are unforeseen factors with a negative impact. This is the self-regulation coefficient; the stronger the self-regulation ability, the better. The larger;

[0112] Self-regulation capability refers to the ability of a platform to ensure data security by adjusting specific parameters in cross-platform collaboration, such as security questions and video authentication.

[0113] The next stage of cross-platform data collaboration security factor is input into the trained artificial intelligence model to predict the next stage of cross-platform data collaboration security level.

[0114] Through the above technical solution, this embodiment provides a method for obtaining the security coefficient of cross-platform data collaboration in the current stage and the next stage. The method calculates the current authentication security coefficient and the data encryption security coefficient based on the current parameters. Then, the cross-platform data collaboration security coefficient in the current stage is calculated based on the authentication security coefficient and the data encryption security coefficient. Finally, the cross-platform data collaboration security coefficient in the next stage is calculated by combining self-adjustment capabilities and sudden environmental factors.

[0115] It should be noted that all parameters in this invention have been dimensionless, all calculations are purely numerical, and the parameters, thresholds, and threshold ranges involved in this invention are all empirical data and need not be elaborated.

[0116] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in the claims, they should all fall within the protection scope of the present invention.

Claims

1. An artificial intelligence-based network security data analysis method, characterized by, The method comprises the following steps: Step S1, collecting cross-platform data collaboration data packets through a network traffic collection device; Step S2, extracting feature parameters in the data packets, and processing all the feature parameters based on artificial intelligence to unify different parameters to the same scale; Step S3, analyzing the feature parameters, and evaluating the security of the current stage of cross-platform data collaboration according to the analysis result; Step S4, predicting the security of the next stage of cross-platform data collaboration according to the analysis result; The specific working process of step S2 comprises: The feature parameters comprise identity verification parameters, data encryption parameters and access transmission parameters; The identity verification parameters comprise password complexity parameters and multi-factor authentication parameters; The data encryption parameters comprise encryption algorithm parameters and key management parameters; The access transmission parameters comprise transmission protocol parameters and data integrity check parameters; The specific working process of step S3 comprises: Step S31, obtaining identity verification, data encryption and access transmission security coefficients respectively; Step S32, obtaining a cross-platform data collaboration security coefficient based on the identity verification, data encryption and access transmission security coefficients; Step S33, comparing the identity verification, data encryption and access transmission security coefficients with system-set identity verification, data encryption and access transmission security coefficient thresholds respectively, if any security coefficient is greater than or equal to the system-set security coefficient threshold, it indicates that the cross-platform data collaboration security is unqualified, if none of the security coefficients is greater than or equal to the system-set security coefficient threshold, step S34 is entered; Step S34, comparing the cross-platform data collaboration security coefficient with a system-set cross-platform data collaboration security coefficient threshold, if the cross-platform data collaboration security coefficient is greater than or equal to the system-set cross-platform data collaboration security coefficient threshold, it indicates that there is a potential risk in the cross-platform data collaboration security; The method for obtaining the cross-platform data collaboration security coefficient in step S32 comprises: A cross-platform data collaboration security coefficient calculation model is constructed, and the expression is: ； In the formula, , and are weight coefficients corresponding to the identity authentication security coefficient, the data encryption security coefficient and the transmission security coefficient, respectively. The working process of step S4 comprises: The present-stage identity authentication parameter, data encryption parameter and access transmission parameter are substituted into the cross-platform data collaboration security coefficient calculation model to obtain a present-stage cross-platform data collaboration security coefficient , and a next-stage cross-platform data collaboration security coefficient calculation model is constructed, and the expression is: ; In the formula, After normalization, the value range is 0 to 1, The next stage of cross-platform data collaboration security coefficient, the value range is 0 to 1, The influence of the burst factor, when there is no burst factor When there is a burst factor and positive impact When there is a burst factor and negative impact , Self-regulation coefficient, the stronger the self-regulation ability The greater; Inputting the next stage cross-platform data collaboration security coefficient into the trained artificial intelligence model to predict the next stage cross-platform data collaboration security level.

2. The network security data analysis method based on artificial intelligence according to claim 1, characterized in that, The working process of obtaining the identity verification security coefficient in step S31 comprises: Obtaining identity verification parameters, and constructing an identity verification security coefficient calculation model based on the identity verification parameters, and the expression is: ； In the formula, is a security factor for identity verification, is a password complexity index factor, is a verification code index factor, and are weight coefficients corresponding to the password complexity index factor and the verification code index factor, respectively.

3. The network security data analysis method based on artificial intelligence according to claim 2, characterized in that, The working process of obtaining the data encryption security coefficient in step S31 comprises: Obtaining data encryption parameters, and constructing a data encryption security coefficient calculation model based on the data encryption parameters, and the expression is: ； In the formula, is an identity authentication security coefficient, is an encryption algorithm index coefficient, is a key management index coefficient, and are weight coefficients corresponding to the encryption algorithm index coefficient and the key management index coefficient, respectively.

4. The network security data analysis method based on artificial intelligence according to claim 3, characterized in that, The working process of obtaining the access transmission security coefficient in step S31 comprises: Obtaining access transmission parameters, and constructing an access transmission security coefficient calculation model based on the access transmission parameters, and the expression is: ； wherein is an access transmission security coefficient, is a transmission protocol index coefficient, is a data integrity check index coefficient, and and are weight coefficients corresponding to the transmission protocol index coefficient and the data integrity check index coefficient, respectively.

Images