Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Akshat Gaurav et al.
Summary: The Internet of Things has gained attention from academics and business information systems. It connects smart devices in an organizational information system and allows them to exchange data. However, the usage of Android apps in IoT devices makes them vulnerable to malware attacks. Researchers have proposed various attack mitigation approaches, and machine learning is considered the most promising strategy due to its accuracy and adaptability.
ENTERPRISE INFORMATION SYSTEMS
(2023)
Review
Computer Science, Theory & Methods
Yue Liu et al.
Summary: Malicious applications, especially those targeting Android, pose a serious threat to developers and end-users. Existing defense approaches based on manual rules or traditional machine learning may not be effective due to the rapid growth of Android malware and the advancement of evasion technologies. Deep learning (DL) techniques have shown promising performance in various domains, so applying DL to Android malware defenses has gained significant research attention. This article presents a systematic literature review that identifies 132 studies from 2014 to 2021, revealing the prevalence of DL-based Android malware detection and other defense approaches based on DL.
ACM COMPUTING SURVEYS
(2023)
Article
Chemistry, Analytical
Osama Khalid et al.
Summary: In recent years, the malware industry has undergone massive development, leading to the emergence of fileless malware which poses a higher threat due to its ability to evade detection techniques. This paper presents a detection technique for fileless malware based on feature analysis using machine learning. The experiments show that the Random Forest algorithm outperforms other classifiers and achieves an overall accuracy of 93.33% in detecting fileless malware from widely used datasets.
Article
Chemistry, Analytical
Juan A. Herrera-Silva et al.
Summary: This research uses dynamic analysis and machine learning to identify evolving ransomware signatures for detecting current and new variants of the threat.
Article
Computer Science, Information Systems
Meng-Han Tsai et al.
Summary: PowerShell has become a common tool for attackers to launch targeted attacks using living-off-the-land tactics and fileless attack techniques. Malicious PowerShell commands are often obfuscated to avoid detection and analysis. To address this challenge, we propose a hybrid framework that combines deep learning and program analysis for automatic de-obfuscation and behavioral profiling of PowerShell commands.
Article
Computer Science, Interdisciplinary Applications
Nitasha Sahani et al.
Summary: ML-based IDS approaches have not been extensively explored in smart grid environments, despite the serious security threats. This article provides an extensive survey on the applications, dataset generation, various ML-based IDSs, evaluation metrics and testbeds, as well as future research directions in the smart grid.
ACM TRANSACTIONS ON CYBER-PHYSICAL SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Jaskaran Singh et al.
Summary: Multiple kinds of ransomware are a growing threat to Internet users. The ransomware encrypts important user data and requires payment of a ransom. The rise of ransomware attacks may be influenced by the trend of crypto-currencies. This article proposes a novel ransomware detection scheme based on Spline Interpolation envisioned Neural Network (SINN-RD) and demonstrates its effectiveness through security analysis and practical implementation, achieving a high accuracy value of 99.83% in comparative study.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Computer Science, Hardware & Architecture
Santosh K. Smmarwar et al.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Christin Alex et al.
Summary: This survey paper compares existing IoT related datasets found in the literature based on their characteristics, attributes, and machine learning techniques used. It provides a comprehensive comparison to help researchers in choosing the appropriate dataset for evaluating their machine learning techniques or designing an IoT security system. The limitations of existing datasets are identified, including the lack of documentation, realistic representation of IoT protocols and attack trends, and representative structures and topologies. To address these limitations, it is recommended to have a standard for dataset documentation and collect datasets from realistic IoT scenarios or real test-beds.
COMPUTERS & SECURITY
(2023)
Article
Automation & Control Systems
Kamran Shaukat et al.
Summary: This paper proposes a novel deep learning-based approach for malware detection, which combines the advantages of static and dynamic analysis to achieve better performance than conventional methods. It converts portable executable (PE) files into colored images and extracts deep features using a fine-tuned deep learning model. Malware is then detected based on these deep features using support vector machines (SVM). The proposed method eliminates the need for intensive feature engineering tasks and domain knowledge, and it is scalable, cost-effective, and efficient.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Huijuan Zhu et al.
Summary: Android has become the most popular mobile operating system due to its open source nature, wide hardware compatibility, and vast application ecosystem. However, its open source nature also makes it a prime target for malware. Existing manual feature-based malware detection methods lack effectiveness and code coverage. To address this, we propose an automated extraction method that characterizes crucial parts of the Dalvik executable into RGB images. Additionally, we introduce MADRF-CNN, a novel CNN variant that incorporates multi-scale context information to capture dependencies between different parts of the image derived from the Dex file. Experimental results demonstrate that our method achieves an accuracy of 96.9%, outperforming state-of-the-art solutions.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Ilker Kara
Summary: This research explores the latest advancements in fileless malware prevention and detection and proposes an analytical approach based on attack strategies and selected sample attributes. The method simplifies feature extraction and reduces processing load, providing advantages for fileless malware detection and system protection against cyber threats.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Princy Victor et al.
Summary: During the past decade, the Internet of Things (IoT) has played a significant role in digitizing society, improving supply chains, and enhancing daily lives. However, the diverse nature of IoT devices has made them vulnerable to malware attacks. In this study, a comprehensive taxonomy of IoT malware is presented, including categories, attack types, distribution architecture, victim devices, characteristics, and more. Additionally, existing works on IoT malware detection are reviewed to provide insights for future researchers.
PEER-TO-PEER NETWORKING AND APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Shuhui Zhang et al.
Summary: As cyber attacks become more complex, fileless malware has become a dangerous and challenging threat. This paper proposes a malware detection approach using convolutional neural network and memory forensics, which can effectively detect malicious code, especially in fileless attacks. By collecting and analyzing executable static samples in memory, the method achieves a high prediction accuracy of up to 97.48%.
Article
Amit Sharma et al.
Journal of Ambient Intelligence and Humanized Computing
(2023)
Article
Computer Science, Hardware & Architecture
Quy Vu Khanh et al.
Summary: This study proposes an efficient edge computing management mechanism for IoT applications in smart cities. By establishing a small database (information map), edge computing servers can store edge service information and exchange it when mobile end-users move to a new edge server's managed coverage. The experimental results have shown that our proposed mechanism significantly improves service response time and energy consumption compared to the traditional mechanism. We hope that this mechanism will be widely applied to sustainable smart cities in the future.
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS
(2023)
Article
Computer Science, Information Systems
Anthony Andreoli et al.
Summary: This paper presents an empirical study of software supply chain attacks (SSCAs) and proposes an investigative framework for identifying and evaluating their characteristic behaviors. Using a large scale dataset of malware, benign software, and Windows 10 binaries, the authors develop a query system to match behaviors and assess the probability of malicious intent. The analysis reveals that the presence of an SSCA behavior within a binary indicates malware with 86-100% probability.
FORENSIC SCIENCE INTERNATIONAL-DIGITAL INVESTIGATION
(2023)
Article
Computer Science, Information Systems
Xabier Saez-de-Camara et al.
Summary: There is an increasing trend of cyberattacks against Internet of Things (IoT) devices, which are becoming more sophisticated and motivated. Traditional IT security mechanisms struggle to integrate with IoT due to its vast scale, diverse hardware and software, and uncontrolled environments. Machine learning methods provide faster response to emerging threats, but face challenges in IoT settings. This work presents an architecture for training unsupervised models for network intrusion detection in distributed IoT and Industrial IoT (IIoT) deployments, leveraging Federated Learning (FL) to reduce isolation and network overhead problems.
COMPUTERS & SECURITY
(2023)
Article
Computer Science, Information Systems
Saddam Hussain Khan et al.
Summary: This paper proposes a new malware detection framework for timely detection of increasingly complex malware attacks in the IoT environment. The framework utilizes innovative convolutional neural networks and ensemble learning to effectively capture global malicious patterns and improve the generalization of hybrid learning. Evaluation on the IOT_Malware dataset demonstrates the robustness and performance of the framework.
COMPUTERS & SECURITY
(2023)
Article
Computer Science, Information Systems
Parnika Bhat et al.
Summary: This paper proposes a precise dynamic analysis approach to identify a variety of malicious attacks. The proposed method focuses on behavioral analysis of malware and uses features such as system calls, binders, and complex Android objects. By employing feature selection and stacking machine learning algorithms, efficient malware detection and classification with an accuracy rate of 98.08% is achieved.
COMPUTERS & SECURITY
(2023)
Article
Computer Science, Artificial Intelligence
ElMouatez Billah Karbab et al.
Summary: To address the issue of ransomware attacks, we propose a new portable framework called SwiftR, which can perform cross-platform ransomware detection and fingerprinting. SwiftR uses advanced deep learning techniques and special feature extraction methods to accurately detect ransomware in both static and dynamic analysis. Extensive evaluation shows that SwiftR achieves excellent performance in ransomware detection, segregation, and family attribution.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sajid Ali et al.
Summary: Despite the increasing threat of IoT-specific malware, assessing IoT systems' security and developing mitigation measures are critical. This study proposes a multitask DL model using LSTM for detecting IoT malware, achieving high accuracy in tasks of determining benign/malicious traffic and identifying malware types. Traffic data from 18 IoT devices were used for training and feature selection enhanced the model's performance.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Salwa Razaulla et al.
Summary: The proliferation of ransomware has become a significant threat to cybersecurity, causing extensive financial, reputational, and operational damage. This paper provides a comprehensive overview of ransomware's evolution, taxonomy, and state-of-the-art research contributions. It highlights the origins and milestones of ransomware, proposes a taxonomy to categorize different types, and reviews existing research on detection, prevention, mitigation, and prediction techniques. The study reveals a lack of emphasis on predicting ransomware and identifies shortcomings in real-time protection and detecting zero-day ransomware, as well as under-researched areas in adversarial machine learning exploitation and concept drift.
Article
Computer Science, Information Systems
Ibrahim Gulatas et al.
Summary: Developing a secure information processing environment requires securing all layers and devices, including Edge/Fog computing environments that rely on securing IoT devices. Recent attacks initiated by IoT malware have had a significant impact on compromised systems due to the large number of infected IoT devices. This study focuses on understanding IoT malware behaviors in the vulnerable layer of Edge/Fog computing environments. A total of 64 IoT malware families have been identified and characterized based on various aspects, providing insights for future research.
Article
Computer Science, Theory & Methods
Harun Oz et al.
Summary: This paper presents a comprehensive survey on ransomware and ransomware defense research with respect to PCs/workstations, mobile devices, and IoT/CPS platforms. It covers 137 studies from 1990 to 2020, providing a detailed overview of ransomware evolution, key building blocks, notable ransomware families, and defense research. The paper also identifies open issues for future research, aiming to motivate further research in the field of ransomware.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Hardware & Architecture
Valerian Rey et al.
Summary: With the increasing number of IoT devices and the growing importance of data privacy and security, researching the application and security issues of federated learning in IoT malware detection becomes crucial. This study explores the use of federated learning to detect malware while preserving data privacy and finds that it has the capability to detect malware, but further efforts are needed to enhance its robustness.
Article
Computer Science, Information Systems
Damien Warren Fernando et al.
Summary: This paper investigates the operation of different genetic and nature-inspired feature selection algorithms in systems where the prediction model changes over time in unforeseen ways. The study proposes a feature selection architecture, FeSA, that is independent of the underlying classification algorithm and aims to improve the longevity of the machine learning classifier. The performance of FeSA is evaluated by introducing concept drift to the trained model, and the results show that the generated feature set remains robust and maintains high detection rates of ransomware malware.
COMPUTERS & SECURITY
(2022)
Article
Computer Science, Hardware & Architecture
Chunlin Xiong et al.
Summary: Advanced Persistent Threat (APT) attacks pose serious security threats and financial losses globally. To tackle the accuracy and efficiency issues in APT detection mechanisms, a novel and accurate detection model is proposed, along with a state-based framework. Experimental results demonstrate that this design can accurately and efficiently detect all attacks in real-world scenarios.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2022)
Article
Computer Science, Information Systems
Durmus Ozkan Sahin et al.
Summary: This study presents a framework for Android malware detection based on permissions, using multiple linear regression methods. Application permissions, critical for the security of the Android operating system, are extracted through static analysis, and machine learning techniques are employed for security analysis. Two classifiers are proposed for permission-based Android malware detection, which are compared with basic machine learning techniques on different datasets. The bagging method is utilized to increase classification performance. The results show remarkable performances with classification algorithms based on linear regression models without the need for complex algorithms.
Article
Computer Science, Information Systems
Marjan Golmaryami et al.
Summary: This article proposes an adversarial self-supervised architecture called SETTI for detecting malware in IoT networks. It introduces three self-supervised attack techniques and a defense method to mitigate these attacks. Experimental results show the impact of different attack methods on malicious sample injection.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Cho Do Xuan et al.
Summary: This research proposes a method of detecting APT malware on workstations based on deep learning graph networks, analyzing and evaluating the behavioral characteristics of malware using graph networks to improve detection efficiency.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Muhammad Shabbir Abbasi et al.
Summary: Ransomware is a type of malware that encrypts data and demands ransom. Behavior-based ransomware detection is challenging due to a large number of system calls in the analysis output. This study presents an automated feature selection method using particle swarm optimization for behavior-based ransomware detection and classification.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Sowmya Myneni et al.
Summary: The growing number of IoT edge devices have caused a change in the cyber-attack landscape, particularly with the significant increase in magnitude and intensity of DDoS attacks. This paper proposes a distributed DDoS detection and mitigation framework, SmartDefense, based on edge computing approaches, to detect and mitigate DDoS attacks at and near the source.
Article
Computer Science, Information Systems
Rajasekhar Chaganti et al.
Summary: In this paper, a deep learning model is proposed to detect and classify IoT malware using ELF binary file byte sequences as input features. The model achieves high accuracy in malware detection and family classification according to the performance evaluation.
COMPUTERS & SECURITY
(2022)
Article
Computer Science, Artificial Intelligence
Ilker Kara et al.
Summary: As information technologies continue to evolve, malware has become more efficient in attacking information systems. Attackers are now utilizing ransomware as a profitable method of cyberattack, encrypting files and demanding ransom for access. Existing security mechanisms have struggled to combat this threat, highlighting the need for more effective detection and analysis methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Theory & Methods
Junwei Tang et al.
Summary: Android malware poses a serious security threat, and obfuscation technology can generate variants that bypass existing detection methods. The proposed MGOPDroid system combines opcode feature extraction, TFIDF algorithm, and deep learning detection model for efficient anti-obfuscation Android malware detection. Experimental results show that the detection accuracy for both unobfuscated and obfuscated malware samples is over 90% with MGOPDroid.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Information Systems
Jiuru Wang et al.
Summary: This paper studies the combination of Attribute-Based Access Control model (ABAC) and blockchain technology, and builds a flexible access control model for right transfer. By using transfer contracts and access control contracts, the massive and dynamic problems of sensor nodes are solved. The idea of Rollup is used to address on-chain storage problems and ensure transparency of operations.
SECURITY AND COMMUNICATION NETWORKS
(2022)
Article
Chemistry, Multidisciplinary
Aldo Hernandez-Suarez et al.
Summary: With the popularity of cryptocurrencies, there is a growing interest in cryptomining services. However, malicious actors have taken advantage of this and illegally mine data. Current solutions have limitations in accurately characterizing network and host samples.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Eduardo Berrueta et al.
Summary: This study proposes a tool to detect and block crypto-ransomware activity based on file-sharing traffic analysis, which can effectively differentiate between ransomware behavior and benign applications, with high detection accuracy and success rate.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Chemistry, Analytical
Fredy Andres Aponte-Novoa et al.
Summary: Cryptojacking is a form of malware that secretly mines cryptocurrencies using the victim's computer resources. This attack has become increasingly prevalent due to the profitability of cryptocurrencies and the difficulty in detecting it. In this study, various machine learning classification models are explored to detect cryptojacking on websites, and feature selection methods are used to improve predictive accuracy.
Article
Computer Science, Information Systems
Weina Niu et al.
Summary: This paper proposes a deep-learning-based malware classification approach that combines time sequence features and association rules features to cope with the increasing number of malware variants. Experimental results demonstrate the effectiveness of the proposed method in accuracy and loss decline rate.
COMPUTERS & SECURITY
(2022)
Article
Computer Science, Information Systems
Ahmad O. Almashhadani et al.
Summary: This study conducts a behavioral analysis of ransomworm network traffic, using WannaCry and NotPetya as case studies, and proposes a reliable and highly accurate multi-feature and multi-classifier network-based system, MFMCNS.
COMPUTERS & SECURITY
(2022)
Article
Computer Science, Theory & Methods
Muhammed Amin Abdullah et al.
Future Generation Computer Systems-The International Journal of eScience
(2022)
Review
Chemistry, Multidisciplinary
Faitouri A. Aboaoja et al.
Summary: The increasing use of digital services has led to the evolution of malicious software, resulting in a higher probability of malware attacks that can corrupt data, steal information, or conduct other cybercrimes. Researchers have proposed various malware detection solutions, but they face challenges in effectively detecting different types of malware, especially zero-day attacks, due to the obfuscation and evasion techniques employed. This survey paper aims to bridge the gap by providing a comprehensive review of malware detection models, introducing a feature representation taxonomy, and linking each detection approach with commonly used data types.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Interdisciplinary Applications
C. Catalano et al.
Summary: The study critically analyzes the strengths and weaknesses of using CNN for static malware detection, starting from the conversion of binary executable files to pixel images. It aims to achieve fast and accurate malware classification by relying solely on the binary content of the file.
COMPUTERS IN INDUSTRY
(2022)
Article
Computer Science, Information Systems
Nan Sun et al.
Summary: Cyber assurance is essential for organizations facing numerous security threats. Utilizing security standards and certifications is an effective strategy for risk management. Through surveying organizations from various countries and sectors, we identified barriers to adoption of Common Criteria and provided recommendations for promoting cybersecurity standards and certifications.
Article
Computer Science, Information Systems
Fatimah Aldauiji et al.
Summary: Ransomware is a highly harmful form of cyber attack that poses major concerns globally. It continues to evolve with advanced techniques, making it difficult for anti-malware detection systems to identify. Cyber threat hunting is a proactive malware detection approach that requires effective threat intelligence and data analysis techniques to enhance detection capabilities.
Article
Computer Science, Information Systems
Alaa Omran Almagrabi
Summary: The Industrial Internet of Things (IIoT) has been widely used in the industry, but security has become a concern. To address this issue, a blockchain-based endpoint protection platform is proposed to validate network policies and reduce latency. Experimental results show that the method performs well in trust management and adapting to hostile environments.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Review
Computer Science, Theory & Methods
Timothy McIntosh et al.
Summary: Although ransomware has evolved aggressively over the years, there is a lack of up-to-date and comprehensive studies evaluating its mitigation techniques. This survey examines the current concept of ransomware, reveals the inadequacies in current research, proposes unified metrics, and evaluates 118 studies to compare their strengths and weaknesses. Future trends and research directions are also forecasted to address the ongoing evolution of ransomware.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Information Systems
Rudra P. Baksi et al.
Summary: Deception is proposed as an effective defense mechanism against Advanced Persistent Threats (APT) in the literature. This paper introduces Decepticon, a defense framework based on Hidden Markov Model using indicators of compromise for detection, to combat APTs in a networked system. The effectiveness of the framework is demonstrated through a real APT ransomware scenario.
INFORMATION SYSTEMS FRONTIERS
(2021)
Article
Computer Science, Information Systems
Craig Beaman et al.
Summary: The COVID-19 pandemic has led to a significant increase in ransomware attacks targeting various institutions. Working remotely in less secure home environments may be a reason for the surge in attacks. Cybercriminals are constantly exploring new approaches, such as social engineering attacks, to spread ransomware.
COMPUTERS & SECURITY
(2021)
Article
Computer Science, Interdisciplinary Applications
Babooshka Shavazipour et al.
Summary: This paper introduces a novel optimization approach for multi-scenario multi-objective robust decision making, and provides an alternative method for scenario discovery and identifying vulnerable scenarios. Testing the approach on the classic shallow lake problem, it is shown that the novel approach ensures feasibility and robust efficiency of solutions under all scenarios while reducing computation cost and addressing scenario-dependency issues. The study also points out the need for novel benchmark problems to properly evaluate novel approaches in reflecting trade-offs and Pareto optimality.
ENVIRONMENTAL MODELLING & SOFTWARE
(2021)
Article
Computer Science, Information Systems
Matilda Rhode et al.
Summary: Traditional perimeter-based detection is no longer effective against malicious software, with the need for endpoint detection and response products for real-time automated response to combat the rapid spread and destructive nature of malware. The proposed model in the study combines statistical filtering and machine learning dynamic behavioral detection model to detect and terminate malicious processes in real-time.
SECURITY AND COMMUNICATION NETWORKS
(2021)
Article
Computer Science, Software Engineering
Yanjie Zhao et al.
Summary: Machine learning techniques play a crucial role in malware detection in the Android realm, but datasets may contain duplicated samples which can skew experimental results. Research shows that sample duplication has a limited impact on supervised learning models, but significantly affects unsupervised learning models.
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY
(2021)
Article
Computer Science, Information Systems
Ahmet Selman Bozkir et al.
Summary: The increasing usage of information systems and online services has led to the emergence of new, more dangerous and harder-to-detect malware. This study proposes a novel approach to identify malware by capturing memory dumps and applying manifold learning schemes to improve detection of unknown malware files.
COMPUTERS & SECURITY
(2021)
Article
Computer Science, Artificial Intelligence
Cho Do Xuan et al.
Summary: APT attacks are malicious attacks with intentional and clear targets, posing challenges to the information security systems of organizations, governments, and businesses. In recent years, the use of machine learning or deep learning algorithms to analyze abnormal behaviors in network traffic for detecting and preventing APT attacks has become popular. However, the lack of typical attack data makes the detection approach using behavior analysis and evaluation techniques difficult.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Theory & Methods
Routa Moussaileb et al.
Summary: Ransomware is a concerning threat in the 21st century, with attackers shifting towards targeted attacks. Numerous detection mechanisms have been proposed, with the article providing a systematic review of countermeasures, defining four stages of the attack and proposing a roadmap for combating ransomware.
ACM COMPUTING SURVEYS
(2021)
Article
Computer Science, Information Systems
Simon R. Davies et al.
Summary: The threat of ransomware is growing, leading to increased costs for victims. This paper presents a technique to identify when encrypted files are being generated, using an enhanced mixed data set. By developing a file classification model based on the differential area between the entropy curves of files under analysis and random data, the model achieved a high success rate in accurately detecting encrypted files.
COMPUTERS & SECURITY
(2021)
Review
Chemistry, Analytical
Sokratis Nifakos et al.
Summary: With the increasing concern of cybersecurity in healthcare, it is crucial for healthcare organizations to enhance staff awareness and training to strengthen cyber defense strategies. The literature highlights the evolving nature of cyber threats and the importance of adopting cybersecurity practices among healthcare professionals.
Article
Chemistry, Multidisciplinary
Walid El-Shafai et al.
Summary: The continuous growth in malicious software development poses significant security threats, prompting researchers to explore efficient malware detection methods using Transfer Learning and Fine-Tuning. By utilizing fine-tuned Convolutional Neural Network models, a visualized multi-classification framework is proposed to address challenges with false positives and imbalanced datasets, achieving high accuracy in detecting malware types.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Adel Abusitta et al.
Summary: The detection and classification of malware are becoming increasingly challenging due to the complexity of malware design and advancements in communication and computing infrastructure. Existing approaches and new analysis methods enable reverse engineers to better understand the functionality and behavior of malware samples, helping them discern intent and attackers' objectives. This survey categorizes and compares findings in malware classification and composition analyses, discussing evasion techniques, feature extraction methods, strengths, limitations, and future research directions.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
Lu-Xing Yang et al.
Summary: The paper introduces a novel APT defense mechanism based on DBAR techniques, aiming to address the shortcomings of the conventional DAR-based APT defense mechanism and demonstrate efficiency in practical implementation.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Information Systems
Chia-Ming Hsu et al.
Summary: Cybersecurity, especially the prevalence of ransomware like crypto-ransomware, is a growing concern that requires continuous research in detection methods and the development of new defense strategies. Studies focusing on machine learning for building detection models and analyzing different encryption techniques are being conducted to address the rising threat of ransomware attacks.
Article
Computer Science, Theory & Methods
Hassaan Irshad et al.
Summary: TRACE is a comprehensive provenance tracking system for scalable, real-time, enterprise-wide APT detection. It utilizes static analysis to identify program unit structures and dependencies, enabling construction of a distributed enterprise-wide causal graph. The system has evolved over a four-year period with improvements focused on performance, scalability, and fidelity, resulting in increased system call coverage and reduced time and space overhead.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2021)
Article
Computer Science, Information Systems
Zainub Mumtaz et al.
Summary: The study focuses on malware construction and various obfuscation techniques, with particular emphasis on garbage code insertion, instruction substitution, and subroutine reordering. The aim is to make detection difficult by implementing techniques that bypass detection, with Hidden Markov Models used to test the effectiveness of code morphing.
Article
Computer Science, Information Systems
Omer Aslan et al.
Summary: In a cloud environment, an intelligent behavior-based malware detection system has been proposed, which can efficiently detect known and unknown malware with high detection and accuracy rates. The research results show that the proposed algorithms, along with machine learning (ML) classifiers, achieve a 99.8% detection rate, 0.4% false positive rate, and 99.7% accuracy.
Article
Computer Science, Information Systems
Danial Javaheri et al.
Summary: This paper presents a novel solution for detecting rare and mutating malware programs and provides a strategy to address the scarcity of datasets for modeling these types of malware. Through the use of genetic algorithms and an optimization strategy, selective generations of mutated elite malware samples are created. The results show a significant improvement in detection accuracy, especially for rare and metamorphic malware.
Article
Computer Science, Information Systems
Jiwon Yang et al.
Summary: The paper introduces a novel method for detecting malicious SSL traffic by reassembling SSL records and inspecting their characteristics using deep learning. The method shows great separability between benign and malicious traffic flows on an encrypted SSL channel.
Article
Computer Science, Information Systems
Luca Caviglione et al.
Summary: Cyber attacks are on the rise, with malicious software being a major factor leading to successful compromises of targeted systems, posing challenges to existing detection techniques. Research indicates that machine learning techniques play a crucial role in malware detection, with future research focusing on development trends in the field and the application of new technologies.
Article
Computer Science, Information Systems
Fernando Rocha Moreira et al.
Summary: This study conducted in a large Brazilian bank utilized the constructivist multicriteria method to address risk planning. The results highlighted the importance of Security Continuous Monitoring controls in cybersecurity risk management. It suggests the adoption of multicriteria methods for risk analysis.
Article
Computer Science, Theory & Methods
Bin Zhang et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2020)
Article
Computer Science, Theory & Methods
Amir Afianian et al.
ACM COMPUTING SURVEYS
(2020)
Review
Computer Science, Hardware & Architecture
Daniel Gibert et al.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2020)
Review
Computer Science, Information Systems
Branka Stojanovic et al.
COMPUTERS & SECURITY
(2020)
Article
Computer Science, Software Engineering
Chee Keong Ng et al.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2020)
Article
Computer Science, Theory & Methods
Aaron Zimba et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2020)
Article
Computer Science, Artificial Intelligence
Cho Do Xuan et al.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2020)
Article
Computer Science, Information Systems
Nabil Moukafih et al.
SECURITY AND COMMUNICATION NETWORKS
(2020)
Article
Automation & Control Systems
Shana Moothedath et al.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2020)
Review
Computer Science, Information Systems
Zhiqiang Wang et al.
Article
Computer Science, Information Systems
Sudhakar et al.
Review
Computer Science, Information Systems
Omer Aslan et al.
Article
Computer Science, Information Systems
Ali Gezer et al.
COMPUTERS & SECURITY
(2019)
Article
Computer Science, Theory & Methods
TaeGuen Kim et al.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2019)
Article
Computer Science, Theory & Methods
Lu-Xing Yang et al.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2019)
Article
Computer Science, Hardware & Architecture
Suhyeon Lee et al.
COMPUTERS & ELECTRICAL ENGINEERING
(2019)
Article
Computer Science, Hardware & Architecture
Prabhakar Krishnan et al.
MOBILE NETWORKS & APPLICATIONS
(2019)
Article
Computer Science, Theory & Methods
Umara Noor et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Computer Science, Theory & Methods
Sajad Homayoun et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Computer Science, Theory & Methods
Hanqi Zhang et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Computer Science, Theory & Methods
Bander Ali Saleh Al-rimy et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Computer Science, Information Systems
Juan Zhao et al.
EURASIP JOURNAL ON INFORMATION SECURITY
(2019)
Article
Computer Science, Information Systems
Adel Alshamrani et al.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2019)
Proceedings Paper
Telecommunications
Da-Yu Kao et al.
2019 21ST INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY (ICACT): ICT FOR 4TH INDUSTRIAL REVOLUTION
(2019)
Proceedings Paper
Computer Science, Theory & Methods
Yonghong Huang et al.
2019 49TH ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS WORKSHOPS (DSN-W)
(2019)
Review
Computer Science, Information Systems
S. Sibi Chakkaravarthy et al.
COMPUTER SCIENCE REVIEW
(2019)
Proceedings Paper
Computer Science, Information Systems
Hugo L. J. Bijmans et al.
PROCEEDINGS OF THE 2019 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (CCS'19)
(2019)
Proceedings Paper
Computer Science, Software Engineering
Jisung Park et al.
PROCEEDINGS OF THE 2019 56TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC)
(2019)
Article
Computer Science, Information Systems
Ibrahim Ghafir et al.
Article
Computer Science, Theory & Methods
Ibrahim Ghafir et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2018)
Article
Computer Science, Information Systems
Jin-Young Kim et al.
INFORMATION SCIENCES
(2018)
Article
Computer Science, Artificial Intelligence
Hui-Juan Zhu et al.
Proceedings Paper
Computer Science, Theory & Methods
Danny Yuxing Huang et al.
2018 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP)
(2018)
Article
Computer Science, Information Systems
Joobeom Yun et al.
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
(2017)
Article
Computer Science, Information Systems
Joobeom Yun et al.
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
(2017)
Article
Multidisciplinary Sciences
Stefan Rass et al.
Article
Computer Science, Theory & Methods
Yanfang Ye et al.
ACM COMPUTING SURVEYS
(2017)
Proceedings Paper
Computer Science, Information Systems
Eugene Kolodenker et al.
PROCEEDINGS OF THE 2017 ACM ASIA CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (ASIA CCS'17)
(2017)
Proceedings Paper
Computer Science, Theory & Methods
Ankur Chowdhary et al.
MTD'16: PROCEEDINGS OF THE 2016 ACM WORKSHOP ON MOVING TARGET DEFENSE
(2016)
Article
Computer Science, Information Systems
Parvez Faruki et al.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2015)