137 results about "Vulnerability assessment" patented technology

The invention discloses a PC bridge service state and vulnerability prediction method based on the Bayesian theory, and relates to the technical field of bridge service state and vulnerability evaluation, and the method comprises the steps: building a three-dimensional finite element model of a bridge; key parameters influencing the service state of the bridge are determined, the three-dimensional finite element model is operated, the mid-span deflection value and the average prestress loss value of each bridge sample at different moments are obtained, and a database is formed; a GRU proxy model for prediction is obtained through database training; aiming at a to-be-studied bridge, obtaining an actually-measured midspan deflection measured value of the bridge; using the key parameters of the bridge and the GRU agent model to obtain a mid-span deflection prediction value of the bridge; performing Bayesian parameter estimation according to the measured value and the predicted value of the mid-span deflection of the bridge, and estimating bridge parameters of the bridge, which conform to posterior probability distribution; and substituting the estimated bridge parameters conforming to the posterior probability distribution into the GRU agent model to obtain a time-varying curve of the mid-span deflection value and the prestress average loss value of the bridge, and a time-varying vulnerability curve of the bridge. According to the method, the relatively accurate bridge key parameters are calculated through Bayesian parameter estimation, and more accurate prediction can be achieved.

Security vulnerability analysis may be performed using policy inference. Application code may have operations that are labeled according to the respective functions that they perform. Some operations may be labeled according to a knowledge database of known operations while others may be inferred through similarity to known operations. The knowledge database may be associated with libraries of programmatic interfaces. Once components of the application code are labeled, a vulnerability database may be that identifies potential vulnerabilities based on data sources, data sinks and threat mitigation operations. Using the labeled operations, one or more potential vulnerabilities may be identified based on labeled data sources and data sinks. The application may then be evaluated for potential security threats based on the identified potential vulnerabilities.

An artificial intelligence-based system for auditing financial services with integrated cybersecurity, comprising: a data collection module configured to gather real-time data from network traffic, system logs, application activity, and multiple financial sources; a vulnerability assessment module employing machine learning (ML) algorithms and configured to accurately and efficiently identify security weaknesses and vulnerabilities; a machine learning engine configured to analyze the gathered financial data to detect anomalies and potential fraud; and a threat prediction module configured to efficiently analyze historical data and current vulnerabilities to accurately predict potential security threats.a remediation recommendation module configured to provide actionable and efficient insights and strategies for mitigating identified vulnerabilities and risks; a cybersecurity module configured for continuous monitoring of financial systems to detect and respond to cybersecurity threats; a compliance module configured to automate the verification of compliance with regulatory standards; a user interface configured to provide real-time monitoring, reporting, and visualization of audit results.

An embodiment includes a method of application vulnerability assessment and prioritization. The method includes ingesting modelling data from data sources for application vulnerabilities. The method includes transforming at least a portion of the modelling data to covariate vectors. The method includes extracting keywords and phrases from the modelling data and statistically measuring relevance of files of the modelling data based on the extracted keywords and phrases. The method includes generating threat levels of the application vulnerabilities based on the covariate vectors and the measured relevance. The method includes outputting the threat levels to a network management system. The method includes implementing, at a first endpoint device of the network, a first patch to address one of the application vulnerabilities.

The present invention discloses a full - probability risk quantitative assessment method for the landslide of a muck yard considering the three - dimensional spatial variability of muck, which includes the following steps: conducting borehole exploration of the muck yard site to obtain muck yard data; obtaining random field parameters characterizing the spatial variability of muck; simulating the three - dimensional spatial variation characteristics of muck; based on the limit equilibrium method, conducting the three - dimensional slope stability assessment of the muck yard and estimating the potential landslide volume; simulating the possible migration ranges under various landslide volumes; statistically collecting the life and property data of downstream disaster - bearing bodies, and based on the vulnerability assessment formulas for buildings and personnel, estimating the vulnerability of disaster - bearing bodies according to the landslide intensity; establishing a full - probability risk assessment formula for the muck yard landslide, and conducting quantitative risk assessment and risk rating. The present invention considers the unique spatial variation characteristics of muck, analyzes the stability, potential sliding position and volume from a three - dimensional perspective, and combines with the quantitative vulnerability assessment method to achieve accurate risk assessment.

The technology of this application relates to a vulnerability assessment method and an analysis device. The analysis device obtains a plurality of pieces of vulnerability information of a computer device. The vulnerability information includes an identifier of a vulnerability, and each piece of vulnerability information indicates one vulnerability on the computer device. A plurality of vulnerabilities indicated by the plurality of pieces of vulnerability information may be on one computer device or different computer devices. The analysis device assesses, based on information about a threat event that is reported by a security device and / or vulnerability exploitation difficulty, threat degrees of the plurality of vulnerabilities to the computer device.

The invention discloses a new energy transmission and distribution collaborative consumption intelligent control method and system, and relates to the technical field of new energy, and the method comprises the steps: collecting real-time monitoring data of each node in a power system, and carrying out the preprocessing; constructing a power grid complex network model according to the adjacent matrix to calculate the power weight of each power transmission line; and storing all data into a relational database and managing the data. According to the method, the nodes and the edges of the power system are accurately modeled, the adjacent matrix is constructed, the power flow of a power grid topological structure and a power transmission line is comprehensively reflected, the load and the operation state of the power grid are accurately evaluated, and errors in a traditional method are avoided; the propagation process of the fault in the power grid is simulated in real time, and the fault propagation rate and range are predicted, so that multi-stage early warning is realized, the accuracy of power grid vulnerability assessment is improved, and the stability and emergency response capability of the power grid are enhanced.

The invention is suitable for the technical field of payment data system vulnerability assessment, and provides a payment data security assessment method and system.The method comprises the steps that after vulnerability scanning and penetration testing operation is conducted on a payment data storage system, a plurality of scanned security defects are determined, and acquiring a preliminary risk priority evaluation index allocated to each security defect, and acquiring a historical operation log of the payment data storage system. According to the method, the mechanism of double correction factors is introduced, so that the repair priority evaluation of the potential risk vulnerabilities in the payment data storage system is optimized. Firstly, in combination with a hysteresis effect correction factor and a secret key updating frequency deviation correction factor, the accuracy and timeliness of vulnerability repair are effectively improved;

A computer implemented method processes vulnerabilities. A processor set identifies a vulnerability and a description of the vulnerability in a vulnerability report. The processor set extracts a set of key exploit conditions for the vulnerability from the description of the vulnerability. The processor set generates a set of different code snippets for the set of key exploit conditions. The processor set searches a set of repositories for a match between the set of components and the set of different code snippets to form a search result. The processor set identifies vulnerability assessment information relating to an applicability of the vulnerability in response to the match between the set of components and the set of different code snippets in the search result.

The invention relates to the technical field of electric power system application, in particular to an electric power CPS vulnerability assessment method and system based on a graph theory, and the method comprises the steps: constructing an unweighted network topology model of an electric power CPS network, and obtaining all nodes of the electric power CPS network, connection edges between the nodes, and load voltage data of all the nodes; obtaining load abnormity of each node of the power CPS network; acquiring voltage recovery responsiveness of each node of the power CPS network; obtaining the operation robustness of each node of the power CPS network; obtaining communities and associated communities of the communities in the power CPS network; acquiring a voltage jump moment sequence of each node in the power CPS network; obtaining the cascade fault degree of each community in the power CPS network; obtaining the cascading criticality of each community in the power CPS network; and obtaining an electric power CPS network vulnerability factor, and evaluating the electric power CPS vulnerability. The risk that the safety of the power system is damaged is reduced.

The invention discloses a vulnerability early warning method and device based on a low-code platform, equipment and a storage medium, and the method comprises the steps: querying a target service weight corresponding to a target service based on a first mapping relation; querying a target environment weight corresponding to the access mode of the target service based on the second mapping relationship; querying a target utilization difficulty weight based on the third mapping relationship; querying a target influence range weight corresponding to the influence range of the target vulnerability based on a fourth mapping relationship; on the basis of the fifth mapping relation, the weight of the target vulnerability is inquired; transmitting each weight to a risk value calculation script, wherein the risk value calculation script is used for calculating a risk value of the target vulnerability based on the received weight information; and determining a risk level corresponding to the target vulnerability according to a risk value returned by the risk value calculation script, and sending vulnerability early warning information when the risk level reaches a preset early warning risk level. According to the invention, the accuracy of vulnerability assessment can be improved and vulnerability early warning can be carried out.

Mechanisms are provided for assessing control checks and components of a vulnerability management system (VMS) for a computing infrastructure. A security vulnerability risk gap assessment of the VMS is executed to generate result data for a plurality of control checks. For each control check, the mechanisms: classify the control check into a maturity level having a corresponding maturity level value; classify each of a plurality of vulnerability assessment security control rating (VASCR) elements into a predetermined classification having corresponding classification values for the control check; and combine the maturity level value and the VASCR element classification values to generate a prioritization score. A graphical user interface output is generated comprising a representation of a prioritized ranked listing of control checks based on the prioritization scores associated with each of the control checks in the plurality of control checks.

The invention discloses a disaster prevention and control refined division method based on map data. The method comprises the following steps: step S10, subdividing an evaluation unit based on map data, landform data and administrative division; step S20, comprehensively selecting prevention and treatment alternative areas through risk assessment, vulnerability assessment and disaster assessment; step S30, constructing an index system from three dimensions of dangerousness, exposure and vulnerability; s40, performing index quantification based on the map data and the investigation and survey data, and calculating the weight of each index in combination with the information entropy; step S50, calculating a comprehensive index of each evaluation unit by adopting a Jenks natural fracture method; and step S60, finely delimiting disaster prevention and control key areas in combination with actual management department experience and comprehensive indexes. The method is convenient for later-period management, avoids a large amount of repeated work, and has relatively high objectivity and reference value.

The present disclosure includes techniques for performing automated vulnerability assessment. The technique includes receiving a designation associated with a Common Vulnerabilities and Exposures (CVE) and retrieving one or more attributes describing the CVE. The technique also includes aggregating, by one or more distributed data acquisition operations, CVE data associated with the CVE, wherein the one or more distributed data acquisition operations electronically capture data from a plurality of networked information sources in parallel, and generating, via a first machine learning model, a prompt data structure based on the CVE designation, the one or more attributes, and the CVE data. The technique further includes transmitting the prompt data structure to a second machine learning model that generates a vulnerability assessment, generating one or more CVE reports based on the vulnerability assessment, and performing an automated remediation action based on the one or more CVE reports.

The invention discloses a software supply chain vulnerability assessment method based on multi-Agent collaboration and dynamic hypergraph learning, which is used for opening a link between vulnerability assessment and repair and realizing full-life-cycle collaboration linkage. For the problem of vulnerability assessment and repair splitting, the method covers the core capabilities of static analysis (SAST), dynamic detection (DAST), interactive analysis (IAST), intelligence analysis and the like. Evaluation results of various agents are output through standardized vulnerability portraits, and a subsequent repair strategy is driven to be automatically generated and executed, so that whole-process closed-loop linkage and fine control of'discovery-evaluation-repair-verification 'of vulnerabilities are realized.

The invention relates to the technical field of information security, in particular to a cloud security vulnerability management platform based on AI. Comprising a centralized management module, a distributed event collector network, an automatic vulnerability assessment system, an intelligent repair suggestion module, an interactive user interface, a self-adaptive vulnerability protection mechanism, a continuous learning and updating mechanism, a multi-level identity verification system, an automatic security test tool set and an extensible plug-in architecture. The AI-based cloud security vulnerability management platform provided by the invention is more comprehensive, intelligent and flexible, so that the problems are solved, and the security of a cloud environment and the use experience of a user are improved.

The invention provides an asset vulnerability repairing method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of security scanning. The repairing method comprises the following steps: identifying potential asset vulnerabilities of an asset association graph at the current moment based on a vulnerability detection fusion model; based on a multi-dimensional vulnerability evaluation model, evaluating a vulnerability score of the potential asset vulnerability at the current moment; and based on the vulnerability score and a repair strategy optimization model, determining a repair plan of the potential asset vulnerability at the current moment. The problems of long time consumption, low efficiency and low timeliness in the process of finding vulnerabilities and taking effective defense measures in related technologies are at least solved. The method is suitable for vulnerability scanning and repairing scenes.

Systems and methods for proactively monitoring the inherent cyber-tech risk of software and hardware components are disclosed. In one embodiment, a method for proactively monitoring a cyber risk of a computer program may include: (1) receiving, by a product / version risk assessment computer program executed by an electronic device and from a user computer program executed by a use electronic device, an identification of a plurality of proposed components to include in the computer program; (2) retrieving, by the product / version risk assessment computer program, vulnerability information for each of the plurality of proposed components, wherein the vulnerability information identifies a security vulnerability for the proposed component; (3) generating, by a product / version risk scoring computer program, a risk score for the computer program under development based on the vulnerability information; and (4) returning, by the vulnerability assessment computer program, the risk score to the user computer program.

Disclosed are configurations to enable reverse engineering and characterizing machine learning algorithms through controlled data manipulation. A target machine learning system is analyzed by obtaining compatible data, applying data poisoning techniques to induce controlled responses, and generating a unique model signature that quantifies the system's response patterns. The model signature is compared against a codebook of known algorithm signatures to identify the underlying algorithm type. The codebook is built and maintained by applying systematic data manipulations, such as data poisoning techniques, to known machine learning algorithms and recording their characteristic responses. Multiple data poisoning techniques may be applied sequentially, with features extracted from the system's responses assembled into multi-dimensional feature vectors. This approach enables identification and vulnerability assessment of machine learning systems without requiring access to their internal structures or source code, supporting both offensive operations to identify vulnerabilities and defensive operations to enhance robustness.

The invention discloses a vulnerability assessment and reinforcement method based on multi-agent cooperative reasoning and related equipment. The method comprises the following steps: a, obtaining reasoning data including reasoning facts and rules; b, taking the penetration test host as an initial node, taking a test target as a termination node, and generating a potential attack path through an attack path reasoning agent; c, removing repeated paths by using an attack path deduplication agent; d, performing prefix sub-path recursive reasoning on the residual paths by the sub-path exploration agent to generate extended attack sub-paths; e, removing repeated paths in the extended sub-paths through a sub-path duplicate removal agent; f, replacing the initial node with the reasoning initial node of the remaining extended sub-paths, recursively executing the steps b to f, exiting the current recursion stage when no new extended sub-path is added, and terminating recursion until no new potential attack path is added, so as to obtain a final attack path set; and g, recording vulnerability utilization frequency in the set, and selecting vulnerability reinforcement according to the vulnerability utilization frequency. According to the method, the problems of insufficient understanding of massive network configuration information, attack path combination explosion and repair decision optimization under service constraints can be solved, and dynamic deduction and active defense of network attack paths are realized.

The invention provides a multi-modal long text vulnerability classification method based on transfer learning and loss adjustment, belongs to the technical field of computers, and solves the technical problems that an existing method is low in classification accuracy and poor in generalization ability. Comprising the following steps: S1, preprocessing a data set; s2, dividing a training set, a verification set and a test set; s3, splicing the bimodal information of the vulnerability description and the code information into long text input, and designing a sliding window segmentation fusion method; s4, finely adjusting the pre-training language model to complete a vulnerability assessment task, and adopting an early stop strategy; s5, migrating knowledge learned in the evaluation task to a vulnerability classification task; s6, designing a dynamic loss function adjustment mechanism to carry out weight adjustment; and S7, inputting test set data into the trained model, and performing vulnerability classification prediction. The method has the beneficial effect that the performance of the vulnerability classification task is improved through transfer learning and loss adjustment.

Techniques are described for assessing container images for vulnerabilities without actually scanning the container images. A vulnerability assessment system (VAS) is described that is configured to perform vulnerabilities assessment for container images. The VAS is configured to perform the vulnerability assessment without scanning the container images. In certain embodiments, the VAS calculates a vulnerability score for the container image where the vulnerability score is indicative of a probability that the container image contains a vulnerability.

The present invention discloses a method for evaluating the progressive collapse vulnerability of structures by combining static and dynamic probabilistic analyses, comprising the following steps: (1) obtaining the design parameters affecting the progressive collapse resistance of the structure; a sample set of design parameters; (2) constructing corresponding static and dynamic progressive collapse deterministic numerical models; establishing corresponding sub-models according to the sample set; (3) performing Pushdown analysis; (4) performing non-linear displacement time history analysis under different load intensities; (5) fitting to obtain the probability density function of the progressive collapse resistance of the structure and calculating the corresponding mean value and standard deviation; (6) fitting to obtain the probability density function of the progressive collapse load effect of the structure and calculating the corresponding mean value and standard deviation; (7) obtaining the scatter points of the progressive collapse vulnerability of the structure; (8) obtaining the progressive collapse vulnerability curve of the structure; the present invention obtains accurate vulnerability assessment results.

A method may include querying, via a processing system, a database comprising a list of cybersecurity threats associated with operational technology (OT) devices within an industrial system. The method may also include identifying OT devices associated with the list of cybersecurity threats, generating scripts configured to confirm that the OT devices are associated with at least one cybersecurity threat of the list of cybersecurity threats, and sending the scripts to the one or more OT devices. The method may then involve determining that the OT devices are associated with the at least one cybersecurity threat based on responses from the OT devices generated based on the scripts, generating instructions for resolving the at least one cybersecurity threat based on a generative artificial intelligence (AI) system, and sending the instructions to one or more devices.

This invention discloses a software vulnerability assessment method, system, and medium based on contrastive learning. The software vulnerability assessment method of this invention includes: training a feature extraction model using a contrastive learning-based training method, wherein the training method includes learning to extract feature vectors of vulnerability attributes by comparing positive and negative samples of vulnerability attributes; extracting feature vectors from the vulnerability attributes of the vulnerability to be assessed using the trained feature extraction model; and classifying the feature vectors using a vulnerability classifier to obtain the classification result of the vulnerability to be assessed. This invention aims to improve the accuracy of software vulnerability assessment by utilizing contrastive learning in the feature extraction process to obtain more effective high-dimensional vulnerability feature representations.

This invention belongs to the field of fan control technology. It provides a laboratory exhaust gas-induced high-altitude jet fan control system, comprising: a multi-source data acquisition module for real-time acquisition of multi-dimensional time-series data related to laboratory exhaust gas emission safety, including fan operating parameters, building environment parameters, exhaust gas source equipment status parameters, and meteorological environment parameters; and a predictive maintenance and early warning module based on the multi-dimensional time-series data. By integrating multi-source data perception, chronic risk trend prediction, system vulnerability assessment based on digital twins, and graded resilience control strategies, a closed loop of "perception-prediction-assessment-decision-execution" is constructed. This achieves early identification, proactive early warning, and adaptive control of coupled risks between "equipment-building-environment-personnel," thereby enhancing the proactive safety capability to prevent toxic exhaust gases from entering the breathing zone of personnel.

The present application relates to the field of power system application technology, and specifically to a graph-theory-based power CPS vulnerability assessment method and system, the method comprising: constructing an unweighted network topology model of a power CPS network, obtaining each node of the power CPS network, the edges between nodes, and the load voltage data of each node; obtaining the load anomaly of each node of the power CPS network; obtaining the voltage recovery responsiveness of each node of the power CPS network; obtaining the operation robustness of each node of the power CPS network; obtaining each community in the power CPS network and the associated communities of each community; obtaining the voltage mutation time sequence of each node in the power CPS network; obtaining the degree of cascading failure of each community in the power CPS network; obtaining the cascading criticality of each community in the power CPS network; obtaining the power CPS network vulnerability factor, and evaluating the power CPS vulnerability. The present application reduces the risk of damage to the safety of the power system.

The invention discloses a method for evaluating vulnerabilities by combining vulnerability codes and vulnerability description texts and using a cross-task attention mechanism. The method comprises the following steps: firstly, for a vulnerability code part, converting the vulnerability code part into a control flow diagram, and generating a plurality of execution paths from the control flow diagram; for the vulnerability description text part, some key vulnerability elements are extracted from the vulnerability description text part; then, considering that seven evaluation tasks have certain relevance, when feature representation of codes and texts is learned, a cross-task attention mechanism is introduced to capture relevance features among the tasks; and finally, carrying out weighted summation on the probability predicted by the classifiers at the code level and the text level to obtain a prediction result of final vulnerability assessment.

A private network is scanned to identify devices, and profiling identified devices for vulnerabilities. A score is determined from a Common Vulnerability Scoring System (CVSS) database for each vulnerability individually that characterizes severity. A score is determined for a collection of vulnerabilities. Exponential tapering functions curb an influence of large numbers of low priority threats on the collection score. The collection threat score increases with severity of the collection of vulnerabilities.

The present invention discloses a method and system for evaluating the vulnerability threat level of power monitoring system equipment, and belongs to the technical field of vulnerability assessment and analysis of power monitoring systems. The method of the present invention comprises: determining a network attack path for key equipment of the power monitoring system, extracting attack behaviors according to the network attack path, and determining the difficulty coefficient of the network attack behavior in combination with the attacker's skills and the configuration evaluation of the attack object; determining the success probability of the network attack under a specific attack cost according to the difficulty coefficient of the network attack behavior; and determining the vulnerability threat level of the key equipment of the power monitoring system subjected to the network attack according to the success probability and the difficulty coefficient of the network attack behavior. The present invention quantitatively evaluates the vulnerability threat level of the key equipment involved in the network attack path, and the evaluation results can provide a technical basis for determining the importance of network assets and the priority of equipment protection deployment.