In recent years, numerous Machine Learning (ML) models, including Deep Learning (DL) and classic ML models, have been developed to detect software vulnerabilities. However, there is a notable lack of comprehensive and...
详细信息
In recent years, numerous Machine Learning (ML) models, including Deep Learning (DL) and classic ML models, have been developed to detect software vulnerabilities. However, there is a notable lack of comprehensive and systematic surveys that summarize, classify, and analyze the applications of these ML models in software vulnerability detection. This absence may lead to critical research areas being overlooked or underrepresented, resulting in a skewed understanding of the current state of the art in software vulnerability detection. To close this gap, we propose a comprehensive and systematic literature review that characterizes the different properties of ML-based software vulnerability detection systems using six major Research Questions (RQs). Using a custom web scraper, our systematic approach involves extracting a set of studies from four widely used online digital libraries: ACM Digital Library, IEEE Xplore, ScienceDirect, and Google Scholar. We manually analyzed the extracted studies to filter out irrelevant work unrelated to software vulnerability detection, followed by creating taxonomies and addressing RQs. Our analysis indicates a significant upward trend in applying ML techniques for software vulnerability detection over the past few years, with many studies published in recent years. Prominent conference venues include the internationalconference on softwareengineering (ICSE), the international Symposium on software Reliability engineering (ISSRE), the Mining software Repositories (MSR) conference, and the ACM internationalconference on the Foundations of softwareengineering (FSE), whereas Information and softwaretechnology (IST), Computers & Security (C&S), and Journal of Systems and software (JSS) are the leading journal venues. Our results reveal that 39.1% of the subject studies use hybrid sources, whereas 37.6% of the subject studies utilize benchmark data for software vulnerability detection. Code-based data are the most commonly used data t
The proceedings contain 49 papers. The topics discussed include: mixed-sensitivity controller design for a tethered UAV-buoy system;cost-effective tweet classification through transfer learning in low-resource NLP set...
ISBN:
(纸本)9798350313826
The proceedings contain 49 papers. The topics discussed include: mixed-sensitivity controller design for a tethered UAV-buoy system;cost-effective tweet classification through transfer learning in low-resource NLP settings;comparing the effectiveness of EMG and electrical impedance myography measurements for controlling prosthetics;home automation system with IoT stack and ChatGPT for people with reduced mobility;detection and prevention of TCP DoS/DDoS attacks in software defined network;design of low cost mini CNC laser engraver;the modified hybrid multi-objective genetic algorithm and loss sensitivity factor for optimal siting and sizing of PV-based distributed generation in distribution networks;energy-efficient UAV-assisted cluster-based control messages relay system in IoT networks;and neural network to predict energy efficiency for space heating in residential buildings.
The proceedings contain 46 papers. The special focus in this conference is on Science, engineering Management and Information technology. The topics include: Verification and Validation of Knowledge engineering System...
ISBN:
(纸本)9783031722837
The proceedings contain 46 papers. The special focus in this conference is on Science, engineering Management and Information technology. The topics include: Verification and Validation of Knowledge engineering Systems: A Life Cycle Framework;The Critical Factors of Success of Gamification in Digital Banking Services: Using Analytic Hierarchy Process (AHP) Approach;e-Shopping Sites Preference Analysis with Multi-criteria Decision-Making Methods;advancing Anemia Diagnosis: Harnessing Machine Learning Methods for Accurate Detection;monkeypox Detection with K-mer Using Machine Learning Algorithms;cloud Computing Model for Handling Medical Big Data: A Mobile Hospital Pervasive Healthcare Application;Harnessing Advanced AI Techniques: An In-Depth Analysis of Machine Learning Models for Improved Diabetes Prediction;image Processing in Toxicology: A Systematic Review;augmented Reality Immersive World with Hologram Special Effect in Early Childhood Education;improving the Visual Ergonomics of Computerised Workplaces Through the Use of Specialised Eye-Rest software;a Diagnosis Model Based on Federated Learning for Lung Cancer Classification;Arrhythmia Detection from ECG Traces Images Using Transfer Learning Approach;enhancing Traffic Flow Prediction in Urban Areas Through Deep Learning and Probe Information: A Comparative Study;an Approach to Multi-agent Deep Q-Network Optimization of Signal Control in Multi-intersection Road Environments to Enhance Urban Traffic Flow;blockchain-Driven Smart Contracts: An Overview of Application Areas and Gap Identification in Construction Management Literature;stochastic Optimization Methodology for Production Planning with Uncertain Demand and Lead Time Based on the Digital Twin;role of Top Management Commitment and Information technology Investment in Digital Transformation;antecedents of Mobile Banking Apps Adoption Among Consumers in Ghana.
The proceedings contain 46 papers. The special focus in this conference is on Science, engineering Management and Information technology. The topics include: Verification and Validation of Knowledge engineering System...
ISBN:
(纸本)9783031722868
The proceedings contain 46 papers. The special focus in this conference is on Science, engineering Management and Information technology. The topics include: Verification and Validation of Knowledge engineering Systems: A Life Cycle Framework;The Critical Factors of Success of Gamification in Digital Banking Services: Using Analytic Hierarchy Process (AHP) Approach;e-Shopping Sites Preference Analysis with Multi-criteria Decision-Making Methods;advancing Anemia Diagnosis: Harnessing Machine Learning Methods for Accurate Detection;monkeypox Detection with K-mer Using Machine Learning Algorithms;cloud Computing Model for Handling Medical Big Data: A Mobile Hospital Pervasive Healthcare Application;Harnessing Advanced AI Techniques: An In-Depth Analysis of Machine Learning Models for Improved Diabetes Prediction;image Processing in Toxicology: A Systematic Review;augmented Reality Immersive World with Hologram Special Effect in Early Childhood Education;improving the Visual Ergonomics of Computerised Workplaces Through the Use of Specialised Eye-Rest software;a Diagnosis Model Based on Federated Learning for Lung Cancer Classification;Arrhythmia Detection from ECG Traces Images Using Transfer Learning Approach;enhancing Traffic Flow Prediction in Urban Areas Through Deep Learning and Probe Information: A Comparative Study;an Approach to Multi-agent Deep Q-Network Optimization of Signal Control in Multi-intersection Road Environments to Enhance Urban Traffic Flow;blockchain-Driven Smart Contracts: An Overview of Application Areas and Gap Identification in Construction Management Literature;stochastic Optimization Methodology for Production Planning with Uncertain Demand and Lead Time Based on the Digital Twin;role of Top Management Commitment and Information technology Investment in Digital Transformation;antecedents of Mobile Banking Apps Adoption Among Consumers in Ghana.
The proceedings contain 93 papers. The topics discussed include: AVIG: a real-time visual inspection for Guava grading system using computer vision and XGBoost;comparison of deep learning methods in detecting hate spe...
ISBN:
(纸本)9798400708503
The proceedings contain 93 papers. The topics discussed include: AVIG: a real-time visual inspection for Guava grading system using computer vision and XGBoost;comparison of deep learning methods in detecting hate speech in Indonesian tweets;learning-augmented K-means clustering using dimensional reduction;optimization of relay node placement in wireless sensor networks (WSN) using A-Star algorithm for random, triangular and rectangular distribution pattern;face emotion recognition system of customer service Using CNN based on embedded system;implementation of fault-tolerance mechanism in quorum-based blockchain provisioning in cloud infrastructure using replication and monitoring protocols;comparative analysis of load balancing with shortest delay and least connection methods on software defined network;and the two types of module access patterns in LMS and their correlation with the students' evaluation.
The proceedings contain 66 papers. The topics discussed include: a prototype development and implementation of a fast lithium battery packs active on-load balancing system;Covid-19 early diagnosis based on transfer le...
ISBN:
(纸本)9798350326642
The proceedings contain 66 papers. The topics discussed include: a prototype development and implementation of a fast lithium battery packs active on-load balancing system;Covid-19 early diagnosis based on transfer learning and modified CNN architecture;a study of audio-to-text conversion software using whispers model;a random forest algorithm for predicting computer programming skill associated with learning styles;an investigation of running load comparisons of ARCore on native android and unity for outdoor navigation system using smartphone;implementation of convolutional neural network in the development of object recognition system;design and implementation of 2-DOF arm manipulator robot as robotic kinematic learning platform;performance prediction and waveform properties of passive coherent location radar systems in the Tarakan area;and a cross-platform implementation of indoor navigation system using unity and smartphone INSUS.
The proceedings contain 54 papers. The special focus in this conference is on internationalconference on Advances in Communication technology and Computer engineering. The topics include: Integration of a UHF Fractal...
ISBN:
(纸本)9783031371639
The proceedings contain 54 papers. The special focus in this conference is on internationalconference on Advances in Communication technology and Computer engineering. The topics include: Integration of a UHF Fractal Antenna into a 1U CubeSat for Low-Earth Orbit Mission;gesture Recognition Based Virtual Mouse and Keyboard;QCNN—A Conceptual Framework for Duplicate Removal in Big Data Using Quality Assured Crowd Sourcing Coupled with Neural Networks;Evaluation of Text Classification Using Support Vector Machine Compare with Naive Bayes, Random Forest Decision Tree and K-NN;a Review on Blockchain Smart Contract Applications;Factors Impacting a UK Based software Business on international Expansion;predicting Fish Habitat in the Persian Gulf Using Artificial Intelligence;junk Mail Content Detection Using Logistic Regression Algorithm;research Protocol for a Preliminary Evaluation of a Gamified Tool for Adult Wellbeing;initial Evaluation of a Mobile Therapeutic Game for Adolescent Anxiety Disorders;help over Harm: Practical and Ethical Considerations for the Evaluation and Deployment of Therapeutic Games;comparative Analysis on the Use of Teleconsultation Using Support: Vector Regression and Decision Tree Regression to Predict Patient Satisfaction;bibliometric Analysis of Scientific Literature on Mental Health Research in Africa;new Technologies and Interventions to Improve the Mental Health of People with Diabetes;robotics Cyber Security Issues;Improving Data Centre Power Efficiency by Applying the VM Consolidation Approach;development and Evaluation of "Perspective: Counselling Simulator": A Gamified Tool for Developing Risk-Assessment Skills in Trainee Counsellors;Online Buying Behaviour of UK University Students;multi-modal Sentiment Analysis Using Text and Audio for Customer Support Centers;preface.
Large Language Models (LLM) is a type of artificial neural network that excels at language-related tasks. The advantages and disadvantages of using LLM in softwareengineering are still being debated, but it is a tool...
详细信息
The omnipresence of software systems across all aspects of society has necessitated that future technology professionals are aware of ethical concerns raised by the design and development of software and are trained t...
详细信息
ISBN:
(纸本)9798350378986;9798350378979
The omnipresence of software systems across all aspects of society has necessitated that future technology professionals are aware of ethical concerns raised by the design and development of software and are trained to minimize harm by undertaking responsible engineering. This need has become even more urgent with artificial intelligence (AI) driven software deployment. In this paper we present a study of an interactive pedagogical intervention - role-play case studies - designed to teach undergraduate technology students about ethics with a focus on software systems. Drawing on the situated learning perspective from the Learning Sciences, we created case studies, associated stakeholder roles, discussion scripts, and pre and post discussion assignments to guide students' learning. Open-ended data was collected from thirty-nine students and analyzed qualitatively. Findings from the study show that by taking on different perspectives on a problem, students were able to identify a range of ethical issues and understand the role of the software system process holistically, taking context, complexity, and trade-offs into account. In their discussion and reflections, students deliberated the role of software in society and the role of humans in automation. The curricula, including case studies, are publicly available for implementation.
From theory and technical skills to self-management and interpersonal skills, and to role-specific knowledge such as DevOps or Requirements engineering, students struggle to become proficient in all aspects to Softwar...
详细信息
ISBN:
(纸本)9798350378986;9798350378979
From theory and technical skills to self-management and interpersonal skills, and to role-specific knowledge such as DevOps or Requirements engineering, students struggle to become proficient in all aspects to softwareengineering before graduating, while instructors struggle to prepare students for industry. Project-based instruction has become a de-facto standard to teach skills and knowledge. Many project-based courses focus on implementation, wherein students tend to adopt third-party technologies without critical reflection. This leads to insufficient knowledge about supply chain risk management (SCRM). The result is that students are inadequately prepared to handle risks to project success due to third-party acquisitions, including usage rights, introduction of security vulnerabilities, or their ability to identify and mitigate acquisition risks. In this paper, we present a capstone-style project-based course to deliver an industry-realistic and teamwork-centric software development approach. We propose incorporating technology Acquisition Plans, which are based on an existing SCRM curriculum, and add acquisition planning, bidding, and risk monitoring activities to the project and development activities. Empirical evaluation and classroom observations show that while students' ability to justify the need for third-party acquisitions remains the same, self-reported ability to evaluate and bid on alternatives is improved. Furthermore, statistically significant improvement can be seen in areas pertaining to risk monitoring, problem detection, and problem resolution.
暂无评论