This paper proposes a mobile application vulnerability detection method based on Code Property Graphs (CPG) and adaptive graph neural networks. The method first converts source code into CPGs, then uses CodeBERT to vectorize CPG nodes. Subsequently, high-level graph features are extracted through graph centrality analysis, and an adaptive graph neural network model combining Transformer's adaptive attention mechanism and Graph Convolutional Networks (GCN) is designed for feature learning and vulnerability detection. Experimental results show that this method achieves an F1 score of 82.9% on real vulnerability datasets, an improvement of 13.6%-49.9% compared to existing methods. Ablation experiments further validate the effectiveness of each key component. This research provides new insights and effective methods based on deep learning for mobile application security, demonstrating high application value and practical significance.

Against the backdrop of highly developed software engineering, code reuse has been widely recognized as an effective strategy to significantly alleviate the burden of development and enhance productivity. However, improper code citation could lead to security risks and license issues. With the source codes of many pieces of software being difficult to obtain, binary code similarity analysis (BCSA) has been extensively implemented in fields such as bug search, code clone detection, and patch analysis. This research selects 39 papers on BCSA from top-tier and emerging conferences within artificial intelligence, network security, and software engineering from 2016 to 2022 for deep analysis. The central focus lies on methods utilizing deep learning technologies, detailing a thorough summary and the arrangement of the application and implementation specifics of various deep learning technologies. Furthermore, this study summarizes the research patterns and development trends in this field, thereby proposing potential directions for future research.

Binary code search is a technique that involves finding code with similarity to a given code within a code database. It finds extensive application in scenarios such as vulnerability queries and code defect analysis. While many existing methods employ advanced machine learning models for similarity analysis, their lack of interpretability and low efficiency in dealing with large-scale functions still remain challenges. To address these issues, we propose a high-efficiency binary code search method called HEBCS. It employs an interpretable approach to extract function-level features and transforms each feature into a locality-sensitive hash representation. Then, the hashes of these features are combined to form the hash of the function. By leveraging the pigeonhole principle, HEBCS enables efficient storage and retrieval of functions, ensuring high execution efficiency even in the presence of large-scale data. Furthermore, we compare HEBCS with a classic method and a state-of-the-art method, demonstrating that HEBCS achieves significantly higher search efficiency while maintaining a comparable accuracy, recall and F1-score. In real-world vulnerability query applications, HEBCS demonstrated promising results. Its effectiveness in large-scale binary function searches suggests significant potential for practical applications.

With the increasing utilization of drones, the cyber security threats they face have become more prominent. Code reuse in the software development of drone systems has led to vulnerabilities in drones. The binary code similarity analysis method offers a way to analyze drone firmware lacking source code. This paper proposes DEGNN, a novel graph neural network for binary code similarity analysis. It uses call-enhanced control graphs and attention mechanisms to generate dual embeddings of functions and predict similarity based on graph structures and node features. DEGNN is effective in cross-architecture tasks. Experimental results show that in the cross-architecture binary function search, DEGNN’s mean reciprocal rank and recall@1 surpass the state of the art by 12% and 28.6%, respectively. In the cross-architecture real-world vulnerability search, specifically targeting drone systems, it has a 33.3% performance improvement over the SOTA model, indicating its great potential in enhancing drone cyber security.

Recent advances in graph neural networks have transformed structural pattern learning in domains ranging from social network analysis to biomolecular modeling. Nevertheless, practical deployments in mission-critical scenarios such as binary code similarity detection face two fundamental obstacles: first, the inherent noise in graph construction processes exemplified by incomplete control flow edges during binary function recovery; second, the substantial distribution discrepancies caused by cross-architecture instruction set variations. Conventional GNN architectures demonstrate severe performance degradation under such low signal-to-noise ratio conditions and cross-domain operational environments, particularly in security-sensitive vulnerability identification tasks where feature instability or domain shifts could trigger critical false judgments. To address these challenges, we propose GBsim, a novel approach that combines graph neural networks with natural language processing. GBsim employs a cross-architecture language model to transform binary functions into semantic graphs, leverages a multilayer GCN for structural feature extraction, and employs a Transformer layer to integrate semantic information, generates robust cross-architecture embeddings that maintain high performance despite significant distribution shifts. Extensive experiments on a large-scale cross-architecture dataset show that GBsim achieves an MRR of 0.901 and a Recall@1 of 0.831, outperforming state-of-the-art methods. In real-world vulnerability detection tasks, GBsim achieves an average recall rate of 81.3% on a 1-day vulnerability dataset, demonstrating its practical effectiveness in identifying security threats and outperforming existing methods by 2.1%. This performance advantage stems from GBsim’s ability to maximize information preservation across architectural boundaries, enhancing model robustness in the presence of noise and distribution shifts.