31 results about "Vulnerability prediction" patented technology

The vulnerability of network devices may be predicted by performing a survival analysis on big data. A prediction algorithm may be built by considering historical data from heterogeneous data sources. The operating state of the network devices on a network may be predicted. The services potentially affected by a predicted outage may be determined and displayed. Alternatively or in addition, the number of clients potentially affected by a predicted outage may be determined and displayed.

The present invention relates to a system for predicting industrial control network vulnerabilities based on summary word segmentation features, and implements step S400, acquiring the text sequence of each sample vulnerability id in the corresponding summary; step S401, comparing Str e Process to get the corresponding word segmentation set A e ; Step S402, when e=1, according to A e The number of participles determines Str e The feature weight w e ; Step S403, when e>1, compare Str e‑1 and Str e , if they are exactly the same, set w e =w e‑1 , if it is not completely consistent, then the participle set A e and participle set A e‑1 Perform the set difference operation to get A e relative to A e‑1 The number of difference participles A e ‑A e‑1 , and A e‑1 relative to A e The number of difference participles A e‑1‑ A e1 , set w e =[(A e ‑A e‑1 ) / (A e‑1‑ A e1 )]*w e‑1 ; Step S404, determine each Str e Corresponding summary characteristic parameter values; step S405, training to obtain an industrial control network vulnerability prediction model, and predicting the industrial control network vulnerability outbreak probability. The present invention can quickly and accurately predict the industrial control network vulnerability outbreak probability and improve the security of the industrial control network.

The present invention relates to a system for predicting loopholes in industrial control networks based on correction parameters, which implements step S201, obtaining P corresponding to each sample loophole id in a preset training period from a database. m The parameter value list, the actual outbreak probability list of Internet vulnerabilities, the actual outbreak probability list of industrial control network vulnerabilities and the true value of the industrial control network vulnerability outbreak probability; step S202, determine the correction parameter P corresponding to each sample vulnerability id CVE , to determine the corresponding training parameter value PC m , PC-based m Generate a model input vector for each sample vulnerability id; step S203, modify the parameter P according to all sample vulnerability ids CVE , training the model input vector and the true value of the vulnerability outbreak probability of the industrial control network to obtain the vulnerability prediction model of the industrial control network; step S204 , predicting the outbreak probability of the vulnerability of the industrial control network based on the vulnerability prediction model of the industrial control network. The invention can quickly and accurately predict the outbreak probability of loopholes in the industrial control network and improve the security of the industrial control network.

The invention discloses an instruction SDC vulnerability prediction method based on support vector regression, the steps are as follows: step 1, perform fault injection experiments on the program set, and obtain a sample data set; step 2, extract the inherent characteristics representing the nature of the instruction itself; step 3. Traversing the sample data set to generate a data propagation dependency path for the target instruction; Step 4, traversing the sample data set to calculate the error masking factor for the target instruction; Step 5, extracting the dependency features of the instruction related to the data propagation dependency; Step 6, Train the instruction SDC vulnerability prediction model based on support vector regression; step 7, extract the target program instruction features, and predict the instruction vulnerability. This method has high prediction accuracy and low performance overhead, and can be effectively applied to the prediction of instruction SDC vulnerability after the program is affected by a transient fault.

The invention discloses a method and system for predicting instruction vulnerability based on deep random forest. The method includes: extracting instruction feature information related to each program instruction and instruction vulnerability, and generating instruction feature vectors representing instruction vulnerability; training program Perform fault injection to obtain the vulnerability value of each program instruction; combine the instruction feature vector and instruction vulnerability value to generate an instruction vulnerability sample data set; perform sliding sampling on the instruction vulnerability sample data set through a sliding window to generate an extended sample data set ; Construct and train an instruction vulnerability prediction model based on deep random forest; extract the instruction feature vector of the target program to be predicted, and combine the instruction vulnerability prediction model to realize the instruction vulnerability prediction of the target program to be predicted. The system is used to implement the above method. The invention has high prediction accuracy, low demand for sample sets and less manual adjustment work, and can be effectively applied to the prediction of instruction vulnerability after a program is affected by a transient fault.

The invention discloses a web application security loophole prediction method based on the execution flow graph. According to the data dependency and control dependency of the web application, the execution flow graph EFG is constructed; the node S where the security-sensitive statement is located is extracted from the EFG k as the end point, with S k The associated user input node U I is the subgraph of the starting point, and extracts the metric element for each subgraph; the specific value of the metric element of the subgraph is used as input, and the S corresponding to the subgraph is k With or without vulnerabilities as the output, a vulnerability prediction model is constructed to realize the prediction of web application security vulnerabilities. The invention includes judgment nodes in the extraction of metric elements, and compared with directly analyzing program slices, the workload is greatly reduced.