BGNN4VD: Constructing Bidirectional Graph Neural-Network for Vulnerability Detection

Large Language Models (LLMs) have gained traction in domains from software development to cybersecurity, particularly for detecting vulnerabilities in program source code. Their ability to analyze large codebases and identify security weaknesses makes them valuable in software security analysis. However, their effectiveness declines in the absence of intermediate representations such as Abstract Syntax Trees (AST), Control Flow Graphs (CFG), and Data Flow Graphs (DFG), or even tokenized forms of code. In this research study, we assess the performance of LLMs in detecting vulnerabilities directly from raw source code, without structural representations. By designing context-specific prompts, we aim to enhance the model's understanding of code semantics. Our findings show that LLMs can partially identify vulnerabilities from raw code alone, reaching up to 43% accuracy. This indicate both the potential and current limitations of prompt-based LLMs for static vulnerability detection.

In recent years, smart contract vulnerability detection methods mostly view smart contract source code as natural language for processing, which cannot fully capture the semantic and structural features of the source code and has a high rate of false positives and missing positives. To improve the accuracy of vulnerability detection, this paper uses Graph Neural Network to obtain the semantic and structural information of the source code and Convolutional Neural Network to assist learning. We propose a graph neural network-based vulnerability detection model for smart contracts, which transforms smart contracts into control flow graphs, learns graph embedding using graph neural networks, and introduces Convolutional Neural Networks to learn the node order information of control flow graphs, and finally performs vulnerability detection using graph embedding and node order information. Experimenting on real datasets, our accuracy and F1 values are improved and the model can effectively detect smart contract vulnerabilities.

During software development and maintenance, vulnerability detection is an essential part of software quality assurance. Even though many program-analysis-based and machine-learning-based approaches have been proposed to automatically detect vulnerabilities, they rely on explicit rules or patterns defined by security experts and suffer from either high false positives or high false negatives. Recently, an increasing number of studies leverage deep learning techniques, especially Graph Neural Network (GNN), to detect vulnerabilities. These approaches leverage program analysis to represent the program semantics as graphs and perform graph analysis to detect vulnerabilities. However, they suffer from two main problems: (i) Existing GNN-based techniques do not effectively learn the structural and semantic features from source code for vulnerability detection. (ii) These approaches tend to ignore fine-grained information in source code. To tackle these problems, in this paper, we propose a novel vulnerability detection approach, named <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MGVD</small> (<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b> <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ultiple</small>-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">raph-Based</small> <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</b> <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ulnerability</small> <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b> <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etection)</small>, to detect vulnerable functions. To effectively learn the structural and semantic features from source code, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MGVD</small> uses three different ways to represent each function into multiple forms, i.e., two statement graphs and a sequence of tokens. Then we encode such representations to a three-channel feature matrix. The feature matrix contains the structural feature and the semantic feature of the function. And we add a weight allocation layer to distribute the weights between structural and semantic features. To overcome the second problem, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MGVD</small> constructs each graph representation of the input function using multiple different graphs instead of a single graph. Each graph focuses on one statement in the function and its nodes denote the related statements and their fine-grained code elements. Finally, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MGVD</small> leverages CNN to identify whether this function is vulnerable based on such feature matrix. We conduct experiments on 3 vulnerability datasets with a total of 30,341 vulnerable functions and 127,931 non-vulnerable functions. The experimental results show that our method outperforms the state-of-the-art by 9.68% – 10.28% in terms of F1-score.

Following advances in machine learning and deep learning processing, cyber security experts are committed to creating deep intelligent approaches for automatically detecting software vulnerabilities. Nowadays, many practices are for C and C++ programs, and methods rarely target PHP application. Moreover, many of these methods use LSTM (Long Short-Term Memory) but not GNN (Graph Neural Networks) to learn the token dependencies within the source code through different transformations. That may lose a lot of semantic information in terms of code representation. This article presents a novel Graph Neural Network vulnerability detection approach, VulEye, for PHP applications. VulEye can assist security researchers in finding vulnerabilities in PHP projects quickly. VulEye first constructs the PDG (Program Dependence Graph) of the PHP source code, slices PDG with sensitive functions contained in the source code into sub-graphs called SDG (Sub-Dependence Graph), and then makes SDG the model input to train with a Graph Neural Network model which contains three stack units with a GCN layer, Top-k pooling layer, and attention layer, and finally uses MLP (Multi-Layer Perceptron) and softmax as a classifier to predict if the SDG is vulnerable. We evaluated VulEye on the PHP vulnerability test suite in Software Assurance Reference Dataset. The experiment reports show that the best macro-average F1 score of the VulEye reached 99% in the binary classification task and 95% in the multi-classes classification task. VulEye achieved the best result compared with the existing open-source vulnerability detection implements and other state-of-art deep learning models. Moreover, VulEye can also locate the precise area of the flaw, since our SDG contains code slices closely related to vulnerabilities with a key triggering sensitive/sink function.

Automated detection of vulnerabilities in source code is an essential cybersecurity challenge, underpinning trust in digital systems and services. Graph Neural Networks (GNNs) have emerged as a promising approach as they can learn the structural and logical code relationships in a data-driven manner. However, the performance of GNNs is severely limited by training data imbalances and label noise. GNNs can often learn “spurious” correlations due to superficial code similarities in the training data, leading to detectors that do not generalize well to unseen real-world data. In this work, we propose a new unified framework for robust and interpretable vulnerability detection—that we call VISION—to mitigate spurious correlations by systematically augmenting a counterfactual training dataset. Counterfactuals are samples with minimal semantic modifications that have opposite prediction labels. Our complete framework includes: (i) generating effective counterfactuals by prompting a Large Language Model (LLM); (ii) targeted GNN model training on synthetically paired code examples with opposite labels; and (iii) graph-based interpretability to identify the truly crucial code statements relevant for vulnerability predictions while ignoring the spurious ones. We find that our framework reduces spurious learning and enables more robust and generalizable vulnerability detection, as demonstrated by improvements in overall accuracy (from 51.8% to 97.8%), pairwise contrast accuracy (from 4.5% to 95.8%), and worst-group accuracy increasing (from 0.7% to 85.5%) on the widely popular Common Weakness Enumeration (CWE)-20 vulnerability. We also demonstrate improvements using our proposed metrics, namely, intra-class attribution variance, inter-class attribution distance, and node score dependency. We provide a new benchmark for vulnerability detection, CWE-20-CFA, comprising 27,556 samples from functions affected by the high-impact and frequently occurring CWE-20 vulnerability, including both real and counterfactual examples. Furthermore, our approach enhances societal objectives of transparent and trustworthy AI-based cybersecurity systems through interactive visualization for human-in-the-loop analysis.

Smart contracts on blockchain platforms are susceptible to security issues that can lead to significant financial losses. This study converts the Solidity code into abstract syntax trees and generates control flow graphs and data flow graphs. These graphs train a graph convolutional network model to detect security weaknesses. The proposed system outperforms traditional tools, achieving higher accuracy, recall, precision, and F1 scores when detecting weaknesses such as integer overflow/underflow, reentrancy, delegate call to the untrusted callee, and time-based issues. This study demonstrates that leveraging control and data flow analysis with graph neural networks significantly enhances smart contract security and provides a robust and reliable solution.

Current software defect prediction and code quality assessment methods treat these inherently related tasks independently, failing to leverage their complementary information. Existing graph-based approaches lack the ability to jointly model structural dependencies and quality characteristics, limiting their effectiveness in capturing the complex relationships between defect patterns and code quality indicators. This paper proposes a novel integrated model that simultaneously tackles both objectives using graph neural networks to leverage the inherent graph structure of software systems. Our novelty lies in the first-of-its-kind integration of multi-level graph representations (AST, CFG, DFG) with a dual-branch attention-based GNN architecture for simultaneous defect prediction and quality assessment. Our approach constructs multi-level graph representations by integrating abstract syntax trees, control flow graphs, and data flow graphs, capturing both syntactic and semantic relationships in source code. The proposed dual-branch GNN architecture employs shared representation learning with attention mechanisms and multi-task optimization to exploit complementary information between defect prediction and quality assessment tasks. Comprehensive experiments on six real-world software projects demonstrate significant improvements over traditional methods, achieving F1-scores of 0.811 and AUC values of 0.896 for defect prediction, while showing 9.3% average improvement in code quality assessment accuracy across multiple quality dimensions. The integration strategy proves effective in capturing complex structural dependencies and provides actionable insights for software development teams, establishing a foundation for intelligent software engineering tools that deliver comprehensive code analysis capabilities.

As a trusted decentralized application, smart contracts manage a large number of digital assets on the blockchain. Vulnerability detection of smart contracts is an important part of ensuring the security of digital assets. At present, many researchers extract features of smart contract source code for vulnerability detection based on deep learning methods. However, the current research mainly focuses on the single representation form of the source code, which cannot fully obtain the rich semantic and structural information contained in the source code, so it is not conducive to the detection of various and complex smart contract vulnerabilities. Aiming at this problem, this paper proposes a vulnerability detection model based on the fusion of syntax and semantic features. The syntactic and semantic representation of the source code is obtained from the abstract syntax tree and control flow graph of the smart contract through TextCNN and Graph Neural Network. The syntactic and semantic features are fused, and the fused features are used to detect vulnerabilities. Experiments show that the detection accuracy and recall rate of this model have been improved on the detection tasks of five types of vulnerabilities, with an average precision of 96% and a recall rate of 90%, which can effectively identify smart contract vulnerabilities.

Internet of Things (IoT) systems are pervasive and increasingly managed through mobile applications. However, poorly designed mobile applications can expose sensitive information to external adversaries. Mitigating such vulnerabilities requires both developers and researchers to apply well-established practices and design secure systems based on clearly defined approaches for vulnerability detection. Although databases such as Open Worldwide Application Security Project (OWASP) and Common Vulnerabilities and Exposures (CVE) catalog known IoT vulnerabilities, no standardised methodology exists for detecting security weaknesses in IoT Mobile applications (IoTMas) during IoT mobile application development. Building on prior research, our research objectives are to: (1) identify, classify, and prioritize critical security vulnerabilities in IoTMAs, (2) survey existing Vulnerability Detection Approaches (VDAs) for IoT mobile applications, (3) critically evaluate the effectiveness of existing VDAs by analyzing their evaluation methodologies and dataset validation, and (4) formulate evidence-based recommendations based on the limitations of existing methods for detecting security vulnerabilities in IoTMAs. We performed a systematic literature review (SLR) from selected primary studies (PSs). From 856 papers retrieved from six academic databases—Scopus, Springer, and Engineering Village, which hosts Compendex (covering IEEE Xplore and the ACM Digital Library), and Inspec (IET)—we reviewed 39 research papers. Our findings include: (1) identification of 52 security vulnerabilities, eight critical (i.e, reported in at least four studies); (2) discovery of seven distinct VDAs; (3) comprehensive VDAs effectiveness evaluation using empirical metrics, accuracy assessments, reproducibility analysis, comparative studies, and validation across diverse IoTMAs marketplaces; (4) recommendations to guide developers and practitioners in selecting appropriate VDAs, thereby supporting the development of secure IoTMAs and enhanced penetration testing. Our study raises awareness of state-of-the-art VDAs, identifies research gaps in existing approaches, and provides recommendations to enhance existing techniques and guide new development, supporting software engineers in making informed technique selection decisions.

Creating deep neural networks for text classification tasks using grammar genetic programming

Remote sensing is a key tool to derive glacier surface velocities but existing mapping methods, such as cross-correlation techniques, can fail where surface properties change temporally or where large velocity variations occur spatially. High-resolution datasets, such as UAV imagery, offer a promising solution to tackle these issues and to study small-scale glacier dynamics, but new workflows are required to handle such data. Therefore, we tested the potential of new deep learning-based image-matching algorithms for deriving glacier surface velocities across the ablation area of a glacier with strong spatial variability in surface velocities (&amp;lt;5 m/yr to &amp;gt;100 m/yr) and substantial changes in surface properties between image acquisitions. For a thorough comparison of state-of-the-art methods and sensors, we applied three different techniques (cross-correlation using geoCosiCorr3D, feature tracking with ORB using SeaIceDrift and the new deep learning-based method using ICEpy4D) and three different platforms (Sentinel-2, PlanetScope, UAVs) to estimate glacier surface velocities. Results showed lowest errors for velocities derived with the deep learning-based approach applied to UAV imagery (RMSE = 2.17 m/yr, R2 = 0.99), followed by cross-correlation using Sentinel-2 images (RMSE = 21.0 m/yr, R2 = 0.59) and the deep learning-based approach with PlanetScope data (RMSE = 21.28 m/yr, R2 = 0.36). Cross-correlation with geoCosiCorr3D resulted in comparably high errors with the UAV dataset (RMSE = 36.22 m/yr, R2 = 0.24), whereas ORB-based feature tacking showed lowest performance with all sensors. Spatial patterns of computed velocities indicate that applying existing cross-correlation methods for areas with regular displacements or low glacier velocities yields suitable results on UAV data, but innovative deep learning-based approaches are required for resolving rapid changes in velocities or in surface properties. This novel method benefits from improved keypoint detection and matching through training using neural networks and data characterized by challenging geometries, outlier minimization and more robust descriptors by applying cross-attention layers. We conclude that continued development of deep learning-based feature tracking approaches for glacier velocity computations may substantially improve UAV-based velocity derivations applied to challenging situations. This method is able to deliver reliable displacement data in situations where traditional methods fail, which implies a new level of detail in understanding and interpreting glacier dynamics.

As software vulnerabilities have surged, efforts to discover them have increased. The syntactic and semantic information of a program is required to detect vulnerabilities. Each information can be represented as a graph, such as Abstract Syntax Tree and Program Dependency Graph. In this paper, the program representations were extracted using various static analysis tools, including Clang Static Analyzer, Joern, and SVF, and compared using Graph Neural Networks to select the appropriate representations for vulnerability detection in C/C++. From the comparison, PDG shows the best performance among the multiple representations. This result indicates a suitable program representation and a tool for vulnerability detection that can be utilized in research utilizing graph neural networks.

Software vulnerabilities pose a significant threat to system security, necessitating effective automatic detection methods. Current techniques face challenges such as dependency issues, language bias, and coarse detection granularity. This study presents a novel deep learning-based vulnerability detection system for Java code. Leveraging hybrid feature extraction through graph and sequence-based techniques enhances semantic and syntactic understanding. The system utilizes control flow graphs (CFG), abstract syntax trees (AST), program dependencies (PD), and greedy longest-match first vectorization for graph representation. A hybrid neural network (GCN-RFEMLP) and the pre-trained CodeBERT model extract features, feeding them into a quantum convolutional neural network with self-attentive pooling. The system addresses issues like long-term information dependency and coarse detection granularity, employing intermediate code representation and inter-procedural slice code. To mitigate language bias, a benchmark software assurance reference dataset is employed. Evaluations demonstrate the system's superiority, achieving 99.2% accuracy in detecting vulnerabilities, outperforming benchmark methods. The proposed approach comprehensively addresses vulnerabilities, including improper input validation, missing authorizations, buffer overflow, cross-site scripting, and SQL injection attacks listed by common weakness enumeration (CWE).

With the widespread application of the Go language, the demand for vulnerability detection in Go programs is increasing. Existing detection models and methods have deficiencies in extracting source code features of Go programs and mainly focus on detecting concurrency vulnerabilities. In response to these issues, we propose a Go program vulnerability detection method based on a graph neural network (GNN). The core of this approach is to utilize GraphSAGE to extract the global structure and deep semantic information of each concurrent function, maximizing the learning of concurrency vulnerability features. To capture contextual information of fine-grained code fragments in source code, we employ taint analysis to extract taint propagation chains and use a Transformer model with a multi-head attention mechanism, based on lexical analysis, to extract fine-grained vulnerability features. We integrate graph-level and token-level features to maximize the detection of various complex types of vulnerabilities in Go source code. Experimental results on a real-world vulnerability dataset demonstrate that our model outperforms existing detection methods and tools, achieving an F1-score of 91.35%. Furthermore, ablation experiments confirm that the proposed feature fusion method effectively extracts deep vulnerability features.

A transformer-based framework for software vulnerability detection using attention-driven convolutional neural networks