365 results about "Control flow" patented technology

The invention relates to the technical field of code security analysis, and discloses a control flow analysis and retrieval enhancement-based large model code security review method, which comprises the following steps of: analyzing an incremental code to generate an abstract syntax tree and data flow analysis information; retrieving local knowledge base association business rules and historical vulnerabilities based on grammatical features, and generating a context enhancement prompt; calling a large language model to jointly analyze codes and contexts, identifying vulnerabilities and outputting a structured report; and combining with a historical false alarm data optimization result and then integrating to a development assembly line. Multi-source information is fused through an RAG technology to enhance semantic understanding, and control flow node tracking and cross-version semantic association are combined, so that the problems of a traditional tool business logic vulnerability detection blind area, incremental code analysis failure and high false alarm rate are solved, synchronous improvement of security examination accuracy and efficiency is realized, and the method is adaptive to an agile development scene.

Techniques and systems described herein relate to monitoring executions of computer instructions on computing devices based on learning and generating a control flow directed graph. The techniques and systems include determining a learned control flow directed graph for executable code of an application by observing executions of transitions during an observation period and determining destinations of indirect transfers based on the learned control flow directed graph. Next a disassembly of the executable code is determined based on the learned control flow directed graph, the destinations of the transfers, and the executable code.

The invention discloses a variation test method and device based on an intelligent automation script. The method comprises the following steps: extracting a statement execution sequence and a branch dependency relationship in an original source code by using a context-aware syntax tree, and generating a control flow diagram and a data flow diagram; performing code semantic analysis on the multi-dimensional code features by using a large language model, identifying potential defect types and variation rules, predicting the test efficiency of variants in combination with a deep Q learning model, and generating to-be-processed variants; performing grammar check and equivalence analysis on the to-be-processed variants to obtain effective variants, and testing the effective variants; variation test indexes are calculated, code weak points are positioned, and test blind areas are identified according to survival variants, so that a visual analysis report is generated; and iteratively generating a new test case according to the current survival variant and the visual analysis report, and testing the current survival variant by using the new test case. According to the invention, the variation test efficiency can be improved.

The invention provides a security code automatic generation method and system based on a full information theory and mechanism ambiguity, and the method comprises the steps: S1, carrying out the feature extraction of a grammar verification layer of an input demand, extracting the grammar features of a code through the topological features of an abstract syntax tree, and carrying out the formalized rule verification of the extracted grammar features; s2, constructing a semantic association model of a cross-code snippet through a semantic analysis layer, and forming a propagation path for tracking a data flow and a control flow; s3, in the pragmatic optimization layer, combining pragmatic constraints of the business scene, and generating a security policy through a dynamic utility function; and step S4, optimizing parameters and security policies of the dynamic utility function through knowledge federal evolution and a closed-loop feedback mechanism. According to the method, a deep collaboration mechanism of grammar, semantic and pragmatic three-dimensional information and a dynamic strategy generation model are reconstructed, security logic is converted from external attributes to endogenous cognitive competence, and the security, interpretability and adaptability of automatic code generation are improved.

The invention discloses a cross-chain smart contract vulnerability detection method and system based on multi-feature fusion learning. The method comprises the following steps: collecting a cross-chain smart contract vulnerability data set for cleaning and labeling; feature extraction is carried out from the source code and the byte code, an abstract syntax tree (AST) is extracted from the cleaned source code, a basic control flow graph (CFG) is extracted from the byte code, and a cross-chain control flow graph (xCFG) is constructed; carrying out feature representation on AST and xCFG, generating a graph vector through a graph neural network (GNN), generating a semantic vector through CodeBert, and fusing the semantic vector into a feature fusion vector; performing model training and detection, taking the generated vectors as training data and test data, obtaining a cross-chain smart contract vulnerability detection model by adopting Transform-FC model training data, and finally evaluating model performance through accuracy, recall rate, precision rate and F1 value. According to the method, the structural features and semantic features of the codes can be effectively fused, potential vulnerability information in the codes can be fully mined, the recognition capability of the model for cross-chain vulnerabilities can be enhanced, and the accuracy and reliability of the cross-chain vulnerability detection model can be improved, so that the security of a block chain system can be more efficiently guaranteed.

The invention provides a software code defect detection method and system based on program code feature fusion, and the method comprises the steps: carrying out the grammar and structure inspection of a code through a static analysis tool, and extracting defect features related to control flow chaos, exception handling and resource leakage; running a preset test case through a dynamic analysis tool, capturing an execution path and an abnormal behavior in a runtime state, and obtaining defect features which are not covered by static analysis; if the output result of the decision tree model is that defects exist, grouping comprehensive defect feature vectors by adopting a density-based clustering algorithm, determining the types and distribution ranges of the defects, and selecting the density clustering algorithm to process defect features in non-spherical distribution; and according to a clustering result, generating a defect repairing suggestion, combining code logic and execution path information, and determining a specific position and an influence range of the defect. According to the method, the stealth defect in the code can be effectively identified and positioned, the software quality and reliability are improved, and timely and accurate defect repairing guidance is provided for developers.

The invention relates to an automatic code auditing method and device, computer equipment and a storage medium. The automatic code auditing method comprises the steps of obtaining a grammar structure, a control flow and a data flow of a to-be-audited code; constructing a context graph of the to-be-audited code according to the grammatical structure, the control flow and the data flow of the to-be-audited code; obtaining a multi-modal collaborative vulnerability detection method, wherein the multi-modal collaborative vulnerability detection method comprises a static analysis method based on rule matching, a symbolic execution method based on a code path, a large model reasoning method based on semantic understanding and weights of the methods; and identifying one or more code vulnerabilities, the vulnerability type of each code vulnerability and the confidence coefficient according to the context graph of the to-be-audited code and the multi-modal collaborative vulnerability detection method. According to the method, the audit codes of various vulnerability types can be processed while the code audit efficiency can be improved.

The invention provides a syntactic structure tree-based code change influence intelligent analysis method and system, and the method comprises the steps: extracting a control flow, a data flow and a call flow according to an AST generated through the analysis of an original code and a changed code, and constructing a static dependency graph SDG containing a multi-dimensional dependency relationship; the method comprises the steps that a base layer is used for comparing AST differences before and after code change and generating grammatical structure change feature vectors; the service layer matches a corresponding service label for the changed AST node by using the service domain template; the change labeling layer constructs a cross-version dependency chain for the change AST nodes and generates historical feature vectors; and calculating a risk value of changing the AST node by utilizing a feature calculation result and combining with a multi-dimensional influence diffusion algorithm, and automatically generating a decision suggestion. According to the method, multiple dimensions of a control flow, a data flow and a call flow are deepened, risk prediction is optimized by utilizing natural language processing and historical change data, and the influence brought by code change is assisted to be better understood and managed.

The invention discloses a program analysis method and device, a readable storage medium and electronic equipment. A to-be-analyzed program is determined, an abstract syntax tree of the to-be-analyzed program is determined through a compiler corresponding to a programming language used by the to-be-analyzed program, nodes in the abstract syntax tree are standardized, and a standard syntax tree is determined. And determining each control flow edge and each data flow edge in the standard syntax tree through the standard syntax tree, adding each control flow edge and each data flow edge to the standard syntax tree, and determining the code attribute graph of the program to be analyzed. The abstract syntax tree is converted into the standard syntax tree, the abstract syntax trees of the programs to be analyzed in different programming languages are unified, and the code attribute graph is constructed based on the standard syntax tree, so that the method can be suitable for program analysis of the programs to be analyzed in various programming languages; different analysis algorithms do not need to be developed for different programming languages, the program analysis efficiency is improved, and the development cost is reduced.

The invention relates to an automatic program repairing method based on data flow driving, which takes an error file and a method signature as input, and reports error information in a defect positioning tool or an integrated development environment. Secondly, handing over error information and original defect codes to a large language model, extracting an element list related to defects from the large language model, then constructing defect contexts, using a search tool to retrieve key element definitions and dependency relationships, integrating control flow and error mode information, and finally obtaining defect information; then, the retrieved information, the original defect codes and the potential defect types are integrated into cue words, and the cue words are submitted to a large language model to generate candidate patches. And then the candidate patch is verified, and if the candidate patch does not pass the verification, error reporting information during the verification is combined with the candidate patch to carry out iterative optimization until the candidate patch successfully passes all test verification or the maximum number of iterations is reached. According to the method, context semantics are enhanced by means of data flow analysis, and the repairing accuracy and efficiency are improved.

The invention discloses a test case generation method and device, equipment and a medium, and relates to the technical field of software test optimization. According to the scheme, the multiple initial test cases are obtained, and the test reports corresponding to the initial test cases are generated through the first preset test tool, so that the time for manually compiling the test cases is effectively shortened; when it is determined that a to-be-supplemented test case of which the corresponding code coverage rate index does not meet a preset requirement exists according to each test report, code uncovered information of the to-be-supplemented test case is determined, and test case optimization parameters are configured in combination with project requirements; and based on the parameter, calling a second preset test tool and a large language model to supplement the to-be-supplemented test case to obtain a complete test case. According to the scheme, the availability of the test case is improved through combination of multiple tools; workflows of test cases covering complex environments such as a function calling relation and a control flow structure are generated by utilizing the inference capability of a large language model, and the code coverage rate of the test cases is remarkably increased.

The invention provides a multi-rule static detection and large-model dynamic repair method for code defects. The method comprises the steps that code defect types are summarized and abstracted into a unified defect mode rule set; constructing an abstract syntax tree, a control flow diagram and a data flow diagram of the source code; performing static analysis based on a multi-rule engine to identify potential defects; inputting the defect context into a large language model to generate a repair suggestion; performing semantic consistency verification and integration on the repair suggestions; and executing automatic testing and secondary static analysis to verify a repair result. According to the method, the traditional static analysis technology and the modern large language model capability are combined, accurate recognition and intelligent repair of code defects are achieved, a closed-loop defect processing flow is formed, the defect detection accuracy is improved, intelligent repair is achieved, closed-loop verification is formed, the development efficiency is improved, and man-machine cooperation is supported.

The invention discloses a cross-language application program vulnerability mining method based on static analysis, which adopts a nested cross-programming language pointer analysis method and a micro-service cross-programming language taint tracking method to effectively solve the limitation of processing nested cross-language control flow and micro-service cross-language data flow. A nested language semantic boundary is accurately positioned by constructing a nested byte code, and a data stream is completely tracked by utilizing an interface relay technology, so that the detection precision is improved. According to the method, part of multi-end data streams and complex control streams of cross-programming language applications can be uniformly processed, and the analysis process in a cross-programming language environment is simplified; by nesting cross-programming language control flow diagram construction and double-end / multi-end data flow diagram construction, a unified analysis framework is constructed, seamless cooperation of static analysis among different languages is achieved, the analysis cost is reduced, the analysis efficiency is improved, efficient and accurate vulnerability mining is achieved in a complex cross-programming language application program, and the method is suitable for application and popularization. And the reliability of cross-language vulnerability detection is improved.

The invention discloses a test generation and defect prediction method and system based on a heterogeneous program diagram, and the method comprises the steps: constructing a heterogeneous dynamic program dependency diagram: extracting an abstract syntax tree, a control flow diagram and a program dependency diagram of a source code through static analysis, capturing an execution track during operation in combination with dynamic instrumentation, and integrating version evolution information, forming a heterogeneous dynamic program dependency graph containing various types of nodes and edges; heterogeneous graph neural network modeling: designing a four-layer eight-header heterogeneous graph neural network model based on the heterogeneous dynamic program dependency graph, and outputting a function level defect probability and a test case sequence by adopting a type awareness attention mechanism and time coding injection; and multi-task joint training and reasoning: adopting an end-to-end training strategy, jointly optimizing defect prediction loss and test generation loss, preferentially screening high-risk functions during reasoning, and generating a coverage test case. According to the method, the defect detection accuracy is remarkably improved, the test coverage rate is increased, and the method is suitable for enterprise-level complex software systems.

The invention discloses a compilation optimization pass combination optimization method based on deep reinforcement learning. The method comprises the following steps: 1) collecting a reference program data set for various general function tests; 2) constructing a deep reinforcement learning-based compilation optimization pass-combination optimization strategy model for a compilation optimization pass-combination optimization process, wherein the compilation optimization pass-combination optimization strategy model comprises agent D3QN construction and definition of a reward space, a state space and an action space; 3) introducing a composite program feature combined with basic features such as a control flow embedding vector extracted by the graph neural network, an instruction number, a basic block number and the like into the expression of the state space, enriching the expression ability of the state, optimizing the pass based on the state selection and acting on the intermediate expression by the D3QN, generating an award, and obtaining the state space; and repeating the loop of feature extraction-action selection-reward generation until the maximum action upper limit is reached, and generating an optimized pass combination adapted to the program features. The problem that in existing compiling optimization, the compiling optimization effect on part of programs is poor is solved.

The invention discloses a computer interactive programming platform automatic evaluation system based on deep learning, and particularly relates to the technical field of deep learning, the system comprises five modules, namely a structure diagram construction module, a semantic diagram generation module, a dynamic evaluation trigger module, a semantic solution identification module and an exponential deduction feedback module, and full-process evaluation from code structure abstraction to semantic modeling is realized. The system dynamically controls a deep evaluation process through a structure matching rate and a logic deviation degree, identifies a potential innovation solution, generates a semantic equivalence degree and a path innovation index, outputs a grade in combination with a neural network score, and embeds a high-innovation sample into a training buffer area to update a model, so as to realize intelligent evaluation and adaptive optimization; according to the method, the modeling precision of a program structure and a control flow is improved, dynamic regulation and control of semantic understanding and an evaluation process are realized, a potential innovation solution can be identified, and model self-updating is realized through scoring grade feedback, so that the intelligent analysis and adaptive evolution capability of an evaluation system on complex programming behaviors is enhanced.

Techniques and systems described herein relate to monitoring executions of computer instructions on computing devices based on learning and generating a control flow directed graph. The techniques and systems include determining a learned control flow directed graph for executable code of an application by observing executions of transitions during an observation period and determining destinations of indirect transfers based on the learned control flow directed graph. Next a disassembly of the executable code is determined based on the learned control flow directed graph, the destinations of the transfers, and the executable code.

The invention provides an intelligent contract vulnerability detection method based on code slices and a neural network, and relates to the technical field of contract vulnerability detection, and the method specifically comprises the following steps: carrying out the static analysis of an intelligent contract code; checking a program execution path through depth-first traversal of the control flow diagram, detecting timestamp dependent vulnerabilities and unchecked external call vulnerabilities, and positioning vulnerability paths in the control flow diagram according to nodes corresponding to vulnerability statements; normalizing the smart contract code, removing smart contract code annotations, unifying variables and function naming, not renaming related state information related variables, converting a smart contract code statement into vector representation, and training and updating a vector; constructing a multilayer graph convolutional neural network as a neural network model for training and detecting vulnerabilities; and outputting a detection result by the multilayer graph convolutional neural network. According to the technical scheme, the problem that the intelligent contract vulnerability cannot be accurately and effectively detected in the prior art is solved.

The invention discloses a mimicry thought-based code dynamic obfuscation compiling method, system and equipment. The method comprises the following steps of: sensing a source code, and performing compiler annotation on a key function in combination with a large language model and expert knowledge; a global character string constant is extracted, an ASCII value of a character is coded into an MBA expression, a decoding function is inserted into a position where the constant is used, mimicry replacement is performed on an original character string in a data segment, and functions of other programs are disguised; adding a clone block irrelevant to function logic, and constructing a mimicry branch by using a dynamic opaque predicate as a jump condition; adding an equivalent heterogeneous shadow branch, and using a random predicate as a jump condition; a flower instruction is inserted, and an MBA expression is used for instruction replacement; and performing control flow flattening on the function. According to the method, the mimicry multi-variant thought is combined, accurate diversified confusion compilation is performed, and key fragments of program codes in the fields of industrial control, power grids, Internet of Things and the like are effectively protected.

Embodiments of the invention provide a compiling method and apparatus, an electronic device and a readable storage medium. The method comprises the steps of converting a branch instruction in a target function into a control flow pseudo instruction related to an architecture of a compiler; performing a first instruction processing operation on any control flow pseudo instruction, and performing a second instruction processing operation on a vector instruction of which the operand type corresponding to the operand is a first preset type; and under the condition that the operand type corresponding to the operand of the control flow pseudo instruction or the vector instruction is a second preset type, determining a target physical predicate register and replacing the virtual predicate register corresponding to the control flow pseudo instruction or the vector instruction with the target physical predicate register. In this way, the number of the generated instructions is reduced, and the running efficiency of the program is improved to a certain extent. The target physical predicate registers are respectively distributed for different control flows, so that the overall execution efficiency of the program is improved, and the parallel execution capability and throughput of the program are improved.

The invention belongs to the technical field of applet privacy leakage detection methods, and discloses an applet privacy leakage detection method and system based on an abstract syntax tree. Decompiling the packaged file of the applet to obtain a source code file; all the logic layer JavaScript files are converted into AST by using an expression analysis library; obtaining a calling dependency graph between a page logic layer file and a tool file layer according to the file reference relationship, obtaining a field-level binding dependency graph of the page logic layer file and the tool file layer according to a data and event binding relationship of the page rendering layer and the page logic layer, and merging the two layers to obtain a global dependency graph; finally, combining the dependency graphs to generate a global dependency relationship graph; dividing the JavaSript code into a plurality of basic blocks according to the dividing rule of the boundary of the control flow, determining the type of the edge according to the information of the boundary, and obtaining a GCFG by combining the dependency graph; and inputting the GCFG into a taint-pointer analysis module, and obtaining a privacy disclosure path according to predefined sink and source libraries and a data flow propagation rule.

The invention discloses an instruction-level code optimization method and device based on template matching, a medium and equipment. According to the method, instruction-level codes serve as input, the input instruction-level codes are firstly constructed into corresponding control flow diagrams, then value ranges of active variables and register quantities are initialized based on the control flow diagrams, then variable assignment instructions and related instructions are found out from instruction sequences of basic blocks to form instruction segments to be optimized, and the instruction segments to be optimized are optimized. The method comprises the following steps of: optimizing an instruction fragment, obtaining an optimized instruction fragment through template matching, performing SMT equivalence verification on the instruction fragment before and after optimization based on an active variable and a value range of a register quantity, and finally optimizing an input instruction-level code in a manner of replacing the instruction fragment before optimization with the optimized instruction fragment which is verified to be equivalent. And finally, the optimized instruction-level code is obtained.

Modifications to existing computer hardware, compiler changes or source-to-source transforms performed during the software build process, and a collection of libraries and modifications to existing standard system software and libraries. The invention allows a program author to enforce various kinds of locality of causality in software to provide enforcement of boundaries for the following aspects of a computer program: control, space, time, modularity, reference, initialization, and mutability. Where these properties do not suffice to guarantee a property at static time, dynamic checks may be added and the constraints on control flow prevent such dynamic checks from being avoided by the program.

The invention discloses a multi-language code generation method based on self-supervised pre-training, which comprises the following steps: acquiring and cleaning multi-language code data to form a training corpus; the method comprises the following steps: representing code data as an abstract syntax tree, extracting a control flow diagram and a data flow diagram of the code data, and obtaining unified semantic representation through combination of a diagram encoder and a sequence encoder; designing a self-supervised pre-training task, and pre-training the semantic representation based on the training corpus; constructing a multi-language pre-training model based on the structure-improved recurrent neural tensor network and the multi-language embedding matrix; when a user inputs a natural language, generating a target language code by using the multi-language pre-training model; and target language code correction is carried out through conventional function testing and grammar checking. According to the method, multi-channel recursive combination and a hierarchical recursive expansion mechanism are combined with self-supervised pre-training, so that accurate generation and performability improvement of cross-language codes are realized.

The invention discloses a cross-modal adaptive fine tuning method and system based on a double-branch network architecture, and realizes cross-modal knowledge fusion and migration by combining the modeling capability of a graph neural network on code graph structures such as an abstract syntax tree, a control flow graph and the like and the powerful semantic understanding and generation capability of a large language model. A double-branch architecture is adopted, a graph structure and text input are coded respectively, and feature interaction is achieved through heterogeneous adaptation, structural decoupling and a mask attention mechanism. In a fine tuning stage, three-stage strategies are provided: basic fine tuning of structure perception, efficient parameter migration by combining Adapter, Prefix Tuning and LoRA, and language generation quality and robustness are optimized based on an unsupervised text reconstruction task. The training stage relates to structure sensing tasks such as node prediction, edge reconstruction and subgraph comparison, and the stability and generalization ability are improved in combination with course learning. The method is widely applicable to tasks such as code completion, question and answer and vulnerability detection, and has the advantages of strong structure perception, efficient cross-modal fusion, low training cost and the like.

The invention discloses an automatic code defect repairing method based on a code attribute graph and a large model, which comprises the following steps: collecting a code sample, analyzing a source code, generating the code attribute graph fusing an abstract syntax tree, a control flow graph and a data flow graph, and then carrying out dynamic pruning according to node importance calculated based on node degrees, PageRank and data propagation dependency, so as to obtain a large model; key nodes are reserved to improve the graph learning efficiency; extracting features of the optimized graph through GAT, introducing multi-scale coding, and generating a graph embedding vector; in combination with node importance, high-value Tokens are screened, semantic embedding of structure perception is carried out, and more accurate text representation is obtained; generating a comprehensive feature by fusing the image and the text vector, and then inserting a mask at a position with weak dependence or high risk; performing fine tuning optimization on the mask position; and inputting the comprehensive features and the mask source codes into a pre-training language model to generate patches, performing multi-task evaluation and reordering, and selecting an optimal patch to complete repair.

The invention relates to the technical field of block chains, in particular to a smart contract vulnerability detection method and system based on a multi-modal large language model.The detection method comprises the steps that S1, the system receives source code input of a smart contract; s2, executing semantic branches and graph structure branches in parallel; executing semantic branch processing, calling an annotation agent, and generating an annotation from the source code of the smart contract; calling a vectorization agent, coding the annotation and the source code, and converting the annotation and the source code into a high-dimensional vector; executing graph structure branch processing, compiling a source code into a byte code by the system, and generating a control flow graph; the vectorization agent generates high-dimensional embedded representation of the nodes based on the control flow graph; and S3, integrating features extracted from the semantic branches and the graph structure branches through a multi-modal feature fusion strategy, and inputting the integrated features into a classifier to detect vulnerabilities. The method is based on a multi-modal large language model agent, and potential vulnerabilities in the smart contract are comprehensively analyzed by integrating high-level semantic information and low-level structured data.

The invention relates to a static analysis-based Pascal-like binary program structured information extraction method, which specifically comprises the following steps of: (1) preliminarily reading basic attributes in a binary file compiled by a Pascal-like by a script and other tools, (2) finding all functions for creating class objects through an obtained construction characteristic function and a control flow analysis technology, and (3) extracting the structured information of the Pascal-like binary program. (3) recursively identifying a member object definition relationship in a binary file and an inheritance relationship between classes by taking a basic object address as a base address and combining a data analysis technology, (4) confirming a corresponding construction function name and a corresponding parameter type and name by combining a result of script automatic generation, and (5) searching a corresponding class interface according to an analysis result, and performing classification and classification on the corresponding construction function. And the code restoration logic is consistent with the original binary file behavior. Accurate restoration of class structures, interfaces and functions is achieved, and therefore the efficiency and accuracy of reverse analysis are improved.

The invention relates to the technical field of kernel fuzz testing, and provides a fuzz test input generation method based on characteristic unification and related equipment, the method comprises the following steps: generating a function call graph and a plurality of control flow graphs of a target system, and integrating the function call graph and all the control flow graphs to obtain an inter-program control flow graph; constructing a kernel code calling chain based on the inter-program control flow diagram; carrying out characteristic unified representation modeling based on the kernel configuration file and the kernel code call chain of the target system, and generating a configuration code relation mapping table; extracting related information of the characteristic related interface function according to the kernel code call chain, and performing grammar conversion based on the related information to generate a system call test protocol template of the characteristic related interface function; and generating fuzzy test input of the target system based on the system call test protocol template and the configuration code relation mapping table. According to the method provided by the invention, the correlation between kernel characteristic configuration and fuzzy test input can be improved.

The invention relates to the technical field of software security, and discloses a variational inference-based micropatch repair path adaptive optimization method, system, device and medium, and the method comprises the steps: constructing a joint control flow diagram and a data flow diagram of a to-be-analyzed program, and forming a program structure diagram; based on the program structure diagram, modeling and sampling potential variables of the repair paths through variational inference, and generating a plurality of candidate repair paths; for each candidate repair path, generating a micropatch statement according to context semantics of each node in the path, and inserting the micropatch statement into a corresponding instrumentation position in the source code; and performing multi-dimensional scoring and sorting on the candidate repair paths, and selecting an optimal repair path for deployment according to a scoring result. According to the method, the structural breakthrough of the whole process is realized in the aspects of path identification, patch generation, strategy optimization, engineering deployment and the like, and a technical support is provided for constructing a software vulnerability repair system with autonomous generation, semantic understanding and controllable deployment capabilities.