A Novel Solutions for Malicious Code Detection and Family Clustering Based on Machine Learning

Yang, Hangfeng; Li, Shudong; Wu, Xiaobo; Lu, Hui; Han, Weihong

doi:10.1109/access.2019.2946482

Cited by 31 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work [ 123 ] deals with two problems related to the detection of malware: (1) the detection of malware signatures from logs (e.g., the xml created when executing an .exe file in a sandbox) for further training of classifiers and (2) the precise detection of groups of mutant malware. To solve the first problem, ensembles of classifiers are proposed.…”

Section: Systematization Of Sa Stages and ML Solutionsmentioning

confidence: 99%

Static Analysis of Information Systems for IoT Cyber Security: A Survey of Machine Learning Approaches

Kotenko

Izrailov

Buinevich

2022

Sensors

View full text Add to dashboard Cite

Ensuring security for modern IoT systems requires the use of complex methods to analyze their software. One of the most in-demand methods that has repeatedly been proven to be effective is static analysis. However, the progressive complication of the connections in IoT systems, the increase in their scale, and the heterogeneity of elements requires the automation and intellectualization of manual experts’ work. A hypothesis to this end is posed that assumes the applicability of machine-learning solutions for IoT system static analysis. A scheme of this research, which is aimed at confirming the hypothesis and reflecting the ontology of the study, is given. The main contributions to the work are as follows: systematization of static analysis stages for IoT systems and decisions of machine-learning problems in the form of formalized models; review of the entire subject area publications with analysis of the results; confirmation of the machine-learning instrumentaries applicability for each static analysis stage; and the proposal of an intelligent framework concept for the static analysis of IoT systems. The novelty of the results obtained is a consideration of the entire process of static analysis (from the beginning of IoT system research to the final delivery of the results), consideration of each stage from the entirely given set of machine-learning solutions perspective, as well as formalization of the stages and solutions in the form of “Form and Content” data transformations.

show abstract

Section: Systematization Of Sa Stages and ML Solutionsmentioning

confidence: 99%

Static Analysis of Information Systems for IoT Cyber Security: A Survey of Machine Learning Approaches

Kotenko

Izrailov

Buinevich

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…e basic framework and process design are as follows. Since this semisupervised learning type detection framework is based on machine learning algorithms, it is similar to the traditional machine learning algorithm [40][41][42][43][44][45], including the training process and the detection process, and the approximate processing of these two processes is shown in Figure 2.…”

Section: Attack Detection Model Framework Based On Semisupervisedmentioning

confidence: 99%

WEB DDoS Attack Detection Method Based on Semisupervised Learning

et al. 2021

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

Since the services on the Internet are becoming increasingly abundant, all walks of life are inextricably linked with the Internet. Simultaneously, the Internet’s WEB attacks have never stopped. Relative to other common WEB attacks, WEB DDoS (distributed denial of service) will cause serious damage to the availability of the target network or system resources in a short period of time. At present, most researches are centered around machine learning-related DDoS attack detection algorithms. According to previous studies, unsupervised methods generally have a high false positive rate, while supervisory methods cannot handle large amount of network traffic data, and the performance is often limited by noise and irrelevant data. Therefore, this paper proposes a semisupervised learning detection model combining spectral clustering and random forest to detect the DDoS attack of the WEB application layer and compares it with other existing detection schemes to verify the semisupervised learning model proposed in this paper. While ensuring a low false positive rate, there is a certain improvement in the detection rate, which is more suitable for the WEB application layer DDoS attack detection.

show abstract

“…We examine the survivability of the network under intentional attacks [32] in this article. Under intentional attacks, important nodes in the network will be attacked.…”

Section: Three Attack Strategiesmentioning

confidence: 99%

Power Grid‐Oriented Cascading Failure Vulnerability Identifying Method Based on Wireless Sensors

Chen

et al. 2021

Journal of Sensors

Self Cite

View full text Add to dashboard Cite

In our paper, we study the vulnerability in cascading failures of the real-world network (power grid) under intentional attacks. Here, we use three indexes ( B , K , k -shell) to measure the importance of nodes; that is, we define three attacks, respectively. Under these attacks, we measure the process of cascade effect in network by the number of avalanche nodes, the time steps, and the speed of the cascade propagation. Also, we define the node’s bearing capacity as a tolerant parameter to study the robustness of the network under three attacks. Taking the power grid as an example, we have obtained a good regularity of the collapse of the network when the node’s affordability is low. In terms of time and speed, under the betweenness-based attacks, the network collapses faster, but for the number of avalanche nodes, under the degree-based attack, the number of the failed nodes is highest. When the nodes’ bearing capacity becomes large, the regularity of the network’s performances is not obvious. The findings can be applied to identify the vulnerable nodes in real networks such as wireless sensor networks and improve their robustness against different attacks.

show abstract

A Novel Solutions for Malicious Code Detection and Family Clustering Based on Machine Learning

Cited by 31 publications

References 33 publications

Static Analysis of Information Systems for IoT Cyber Security: A Survey of Machine Learning Approaches

Static Analysis of Information Systems for IoT Cyber Security: A Survey of Machine Learning Approaches

WEB DDoS Attack Detection Method Based on Semisupervised Learning

Power Grid‐Oriented Cascading Failure Vulnerability Identifying Method Based on Wireless Sensors

Contact Info

Product

Resources

About