Dynamic analysis of malware using artificial neural networks: Applying machine learning to identify malicious behavior based on parent process hirarchy

Pascariu, Cristian; BARBU, Ionuț-Daniel

doi:10.1109/ecai.2017.8166505

Cited by 6 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ANN is designed to simulate the working of human brain in processing of incoming information. In pattern recognition process, the ANN gathers their knowledge from the experiments on determined data training [29]. In this research work, the ANN architecture consists of 2 Hidden layers, where the numbers of neurons in each layer are 50 neurons, while Input layer has 5 neurons.…”

Section: Classificationmentioning

confidence: 99%

IoT botnet attack detection using deep autoencoder and artificial neural networks

2023

KSII TIIS

View full text Add to dashboard Cite

As Internet of Things (IoT) applications and devices rapidly grow, cyber-attacks on IoT networks/systems also have an increasing trend, thus increasing the threat to security and privacy. Botnet is one of the threats that dominate the attacks as it can easily compromise devices attached to an IoT networks/systems. The compromised devices will behave like the normal ones, thus it is difficult to recognize them. Several intelligent approaches have been introduced to improve the detection accuracy of this type of cyber-attack, including deep learning and machine learning techniques. Moreover, dimensionality reduction methods are implemented during the preprocessing stage. This research work proposes deep Autoencoder dimensionality reduction method combined with Artificial Neural Network (ANN) classifier as botnet detection system for IoT networks/systems. Experiments were carried out using 3layer, 4-layer and 5-layer pre-processing data from the MedBIoT dataset. Experimental results show that using a 5-layer Autoencoder has better results, with details of accuracy value of 99.72%, Precision of 99.82%, Sensitivity of 99.82%, Specificity of 99.31%, and F1-score value of 99.82%. On the other hand, the 5-layer Autoencoder model succeeded in reducing the dataset size from 152 MB to 12.6 MB (equivalent to a reduction of 91.2%). Besides that, experiments on the N_BaIoT dataset also have a very high level of accuracy, up to 99.99%.

show abstract

Section: Classificationmentioning

confidence: 99%

IoT botnet attack detection using deep autoencoder and artificial neural networks

2023

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…In the field of cyber security, machine learning methods such as K-Nearest Neighbor (KNN), Naive Bayes Classifier, Decision Tree and Support Vector Machine (SVM) have proven to be indispensable tools in revealing malicious intentions of heterogeneous structures [2]. There were many studies that produced different solutions to detect and eliminate malware [3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach to Malware Detection Using Application Programming Interface Calls (MDAPI)

Yuksel,

2023

View full text Add to dashboard Cite

Today, all kinds of institutions and organizations depend on the Internet and information systems. They have been an inseparable part of human life. This brings out not only convenience, but also potentially devastating vulnerabilities. There are countless solutions for such risks and it is true that these solutions greatly contribute to security, but no effective solution has yet been found against Zero-Day malware. Zero-day malware is malicious software that has not yet been identified by competent authorities and is not classified as malicious software. A traditional malware detection tool can only detect previously detected software and classify it as malicious. Machine learning methods, which have proven effective in various domains, offer a promising approach to addressing Zero-Day malware. Throughout this study, a stable solution other than traditional methods have been investigated to overcome all kinds of malware. Instead of solutions consisting of complex, time-consuming and heterogeneous features (such as deleting/adding/changing files, monitoring registry records, or running processes) in various studies in the literature, a simple, low-time cost and stable solution with homogeneous features (only API calls) has been obtained. The 98.04% accuracy score shows that the method is quite successful. The importance of the study is having high accuracy using only API calls as features in malware detection. It has been realized that classical antivirus methods are no longer sufficient for combating malicious software.

show abstract

Economic Indicators of the Algorithm for Introducing Artificial Intelligence into the Automated Process Control System

Vlasov

Lapteva

2022

Lecture Notes in Information Systems and Organisation

View full text Add to dashboard Cite

Dynamic analysis of malware using artificial neural networks: Applying machine learning to identify malicious behavior based on parent process hirarchy

Cited by 6 publications

References 2 publications

IoT botnet attack detection using deep autoencoder and artificial neural networks

IoT botnet attack detection using deep autoencoder and artificial neural networks

A Machine Learning Approach to Malware Detection Using Application Programming Interface Calls (MDAPI)

Economic Indicators of the Algorithm for Introducing Artificial Intelligence into the Automated Process Control System

Contact Info

Product

Resources

About