A5102926361- Software Engineering Research
- Advanced Malware Detection Techniques
- Software Testing and Debugging Techniques
- Software Reliability and Analysis Research
- Security and Verification in Computing
- Web Application Security Vulnerabilities
- Adversarial Robustness in Machine Learning
- Topic Modeling
- Software System Performance and Reliability
- Real-time simulation and control systems
- Anomaly Detection Techniques and Applications
- Digital Marketing and Social Media
- Online Learning and Analytics
- Advanced Data Compression Techniques
- Real-Time Systems Scheduling
- Cloud Computing and Resource Management
- Explainable Artificial Intelligence (XAI)
- Rough Sets and Fuzzy Logic
- Oil Spill Detection and Mitigation
- Infrared Target Detection Methodologies
- Ethics and Social Impacts of AI
- Advanced Measurement and Detection Methods
- Advanced Wireless Communication Techniques
- Dental Health and Care Utilization
- Video Coding and Compression Technologies
Yangzhou University
2021-2024
Hebei University
2023
Shanghai University of Finance and Economics
2021
Northwestern Polytechnical University
2017
Recently, with the widespread use of deep neural networks (DNNs) in high-stakes decision-making systems (such as fraud detection and prison sentencing), concerns have arisen about fairness DNNs terms potential negative impact they may on individuals society. Therefore, testing has become an important research topic DNN testing. At same time, network coverage criteria based neuronal activation) is considered adequacy test for white-box It implicitly assumed that improving can enhance quality...
Java deserialization vulnerability is a severe threat in practice. Researchers have proposed static analysis solutions to locate candidate vulnerabilities and fuzzing generate proof-of-concept (PoC) serialized objects trigger them. However, existing limited effectiveness efficiency.In this paper, we propose novel hybrid solution ODDFuzz efficiently discover vulnerabilities. First, performs lightweight taint identify gadget chains that may cause In step, tries all candidates avoid false...
Java (de)serialization is prone to causing security-critical vulnerabilities that attackers can invoke existing methods (gadgets) on the application's classpath construct a gadget chain perform malicious behaviors. Several techniques have been proposed statically identify suspicious chains and dynamically generate injection objects for fuzzing. However, due their incomplete support dynamic program features (e.g., runtime polymorphism) ineffective object generation fuzzing, are still far from...
Recently, Graph Neural Network (GNN)-based vulnerability detection systems have achieved remarkable success. However, the lack of explainability poses a critical challenge to deploy black-box models in security-related domains. For this reason, several approaches been proposed explain decision logic model by providing set crucial statements positively contributing its predictions. Unfortunately, due weakly-robust and suboptimal explanation strategy, they danger revealing spurious...
Vulnerabilities can have devastating effects on information security, affecting the economy, social stability, and national security. The idea of automatic vulnerability detection has always attracted researchers. From traditional manual mining techniques to static dynamic detection, all rely human experts for feature definition. rapid development machine learning deep alleviated tedious task manually defining features by while reducing lack objectivity caused subjective awareness. However,...
Memory-related vulnerabilities can result in performance degradation or even program crashes, constituting severe threats to the security of modern software. Despite promising results deep learning (DL)-based vulnerability detectors, there exist three main limitations: (1) rich contextual semantics related have not yet been fully modeled; (2) multi-granularity features hierarchical code structure are still hard be captured; and (3) heterogeneous flow information is well utilized. To address...
Abstract Vulnerability classification is a significant activity in software development and maintenance. Natural Language Processing (NLP) techniques, which utilize the descriptions public repositories, are widely used automatic vulnerability classification. However, ordinarily short contain many technical terms, making them difficult for machines to automatically comprehend. In this paper, we present an approach based on triggers classify vulnerabilities. First, extract with Bert Question...
Abstract With the rapid development of information age, software vulnerabilities have threatened safety communication and mobile network, research on vulnerability repair is urgent. Different from existing machine learning-based approaches, we propose VulRep , a approach based introduction, which combines empirical findings inducing fixing commit with learning approaches for repair. Firstly, construct introduction dataset, generate AST tree code to form sequence after abstraction processing,...
Context: As software evolves, the test suite tends to grow, regression testing has become prohibitively expensive. Test minimization is one of most important approaches for reducing cost. The process a trade-off between cost and other value criteria appropriate be described as many-objective optimization problem. Objective: To identify efficient redundant degree data improving efficiency without decreasing defect detection ability data. Method: We introduce mutation testing-based approach,...
Abstract Vulnerabilities in the source code of software are critical issues realm engineering. Coping with vulnerabilities is becoming more challenging due to several aspects such as complexity and volume. Deep learning has gained popularity throughout years a means addressing issues. This paper proposes an evaluation vulnerability detection performance on representations evaluates how machine (ML) strategies can improve them. The structure our experiment consists three deep neural networks...
Bug localization is an important field in software engineering research. The traditional bug approaches based on information retrieval separate words through lexical analysis. In this way, the comments of source code are ignored or treated as plain text, which will lose some semantic information. paper, MBL_SHL, automatic Method-level Localization approach, utilises Summarization, Historical fixed bugs and Length, presented. Based summarization technology, approach first supplements comment...
Abstract An automated task for finding the essential buggy files among software projects with help of a given bug report is termed localization. The conventional approaches suffer from challenges performing lexical matching. Particularly, terms utilized describing bugs in reports are observed to be irrelevant used source code files. To resolve these problems, we propose an optimized and ensemble deep learning model These features reduced by principle component analysis (PCA). Then, they...
<title>Abstract</title> Previous studies have noted a distinct seasonal variation in oral diseases, which appeared to align with the patterns of climate change. This observation sparked our interest investigating whether there is definitive correlation between ambient temperature fluctuations and incidence diseases different climatic cities China, connection that, date, remains unclear. study aimed elucidate relationship diseases. Daily outpatient data from Affiliated Stomatological Hospital...