Malware poses a significant threat to computer systems and networks. This necessitates the development of effective detection mechanisms. Detection mechanisms dependent on signatures for attack detection perform poorly due to high false negatives. This limitation is attributed to the inability to detect zero-day attacks, polymorphic malware, increasing signature base, and detection speed. To achieve rapid detection, automated system-level malware detection using machine learning approaches, leveraging the power of artificial intelligence to identify and mitigate malware attacks, has emerged as a promising solution. This comprehensive review aims to provides a detailed analysis of the status quo in malware detection by exploring the fundamentals of machine learning techniques for malware detection. The review is largely based on the PRISMA approach for article search methods and selection from four databases. Keywords were identified together with inclusion and exclusion criteria. The review seeks feature extraction and selection methods that enhance the accuracy and precision of detection algorithms. Evaluation metrics and common datasets were used to assess the performance of the system-level malware detection techniques. A comparative analysis of different machine learning approaches, emphasizing their strengths, weaknesses, and performance in detecting system-level malware is presented together with the limitations of the detection techniques. The paper concludes with future research opportunities, particularly in applying artificial intelligence, and provides a resource for researchers and cybersecurity professionals seeking to understand and advance automated system-level malware detection using machine learning.

Intrusion and malware detection tasks on a host level are a critical part of the overall information security infrastructure of a modern enterprise. While classical host-based intrusion detection systems (HIDS) and antivirus (AV) approaches are based on change monitoring of critical files and malware signatures, respectively, some recent research, utilizing relatively vanilla deep learning (DL) methods, has demonstrated promising anomaly-based detection results that already have practical applicability due low false positive rate (FPR). More complex DL methods typically provide better results in natural language processing and image recognition tasks. In this paper, we analyze applicability of more complex dual-flow DL methods, such as long short-term memory fully convolutional network (LSTM-FCN), gated recurrent unit (GRU)-FCN, and several others, for the task specified on the attack-caused Windows OS system calls traces dataset (AWSCTD) and compare it with vanilla single-flow convolutional neural network (CNN) models. The results obtained do not demonstrate any advantages of dual-flow models while processing univariate times series data and introducing unnecessary level of complexity, increasing training, and anomaly detection time, which is crucial in the intrusion containment process. On the other hand, the newly tested AWSCTD-CNN-static (S) single-flow model demonstrated three times better training and testing times, preserving the high detection accuracy.

Information technology (IT) security risk analysis preventatively helps organizations in identifying their vulnerable systems or internal controls. Some researchers propose expert systems (ES) as the solution for risk analysis automation since risk analysis by human experts is expensive and timely. By design, ES need a knowledge base, which must be up to date and of high quality. Manual creation of databases is also expensive and cannot ensure stable information renewal. These facts make the knowledge base automation process very important. This paper proposes a novel method of converting attack trees to a format usable by expert systems for utilizing the existing attack tree repositories in facilitating information and IT security risk analysis. The method performs attack tree translation into the Java Expert System Shell (JESS) format, by consistently applying ATTop, a software bridging tool that enables automated analysis of attack trees using a model-driven engineering approach, translating attack trees into the eXtensible Markup Language (XML) format, and using the newly developed ATES (attack trees to expert system) program, performing further XML conversion into JESS compatible format. The detailed method description, along with samples of attack tree conversion and results of conversion experiments on a significant number of attack trees, are presented and discussed. The results demonstrate the high method reliability rate and viability of attack trees as a source for the knowledge bases of expert systems used in the IT security risk analysis process.

The increasing amount of malware and cyberattacks on a host level increases the need for a reliable anomaly-based host IDS (HIDS) that would be able to deal with zero-day attacks and would ensure low false alarm rate (FAR), which is critical for the detection of such activity. Deep learning methods such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are considered to be highly suitable for solving data-driven security solutions. Therefore, it is necessary to perform the comparative analysis of such methods in order to evaluate their efficiency in attack classification as well as their ability to distinguish malicious and benign activity. In this article, we present the results achieved with the AWSCTD (attack-caused Windows OS system calls traces dataset), which can be considered as the most exhaustive set of host-level anomalies at the moment, including 112.56 million system calls from 12110 executable malware samples and 3145 benign software samples with 16.3 million system calls. The best results were obtained with CNNs with up to 90.0% accuracy for family classification and 95.0% accuracy for malicious/benign determination. RNNs demonstrated slightly inferior results. Furthermore, CNN tuning via an increase in the number of layers should make them practically applicable for host-level anomaly detection.

Malware intrusion is a serious threat to cybersecurity; that is why new and innovative methods are constantly being developed to detect and prevent it. This research focuses on malware intrusion detection through the usage of system calls and machine learning. An effective and clearly described system-call grouping method could increase the various metrics of machine learning methods, thereby improving the malware detection rate in host-based intrusion-detection systems. In this article, a risk-based system-call sequence grouping method is proposed that assigns riskiness values from low to high based on function risk value. The application of the newly proposed grouping method improved classification accuracy by 23.4% and 7.6% with the SVM and DT methods, respectively, compared to previous results obtained on the same methods and data. The results suggest the use of lightweight machine learning methods for malware attack can ensure detection accuracy comparable to deep learning methods.

The expansion of operation technology (OT) use and its tight integration with classical information and communication technologies have led not only to additional and improved possibilities in monitoring physical/manufacturing processes and the emergency of Industry 4.0 but also to a number of new threats, both related to the security of processed data and the safety of people, affected by physical processes and controlled by OT. Understanding potential threats has caused an increased demand for scientific research in the field, which is still relatively new and lacks established terminology. In this review paper, we aim to identify emerging trends and technologies in OT incident response, attack detection, applications of machine and deep learning for attack recognition, and security of OT protocols. An examination of research patterns from the Web of Science repository is performed to comprehend the panorama of publications and the present state of research in the area of OT security. The analysis shows a notable rise in publications concerning OT security, reflecting an increasing research interest. Proceeding articles and research articles were the predominant types of publications that were analyzed. The analysis further emphasizes the collaborative connections between researchers, academic institutions, and nations. Additionally, co-occurrence and citation analyses are carried out to offer an understanding of the associations between various keywords and/or research subjects. The study is finalized by suggesting future research directions on OT security. The uniqueness of this review lies in its focus on OT rather than the more commonly explored SCADA/ICS topics, attempting to cover a wider range of research topics instead of concentrating on a narrow area/method.