Malicious Code Detection based on Image Processing Using Deep Learning

Kumar, Rajesh; Zhang, Xiaosong; Khan, Riaz Ullah; Ahad, Ijaz; Kumar, Jay

doi:10.1145/3194452.3194459

Cited by 46 publications

(22 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep learning method using convolutional neural network was employed by Kumar et al at [42] to identify unknown malware programs. The authors visualized malicious codes in the form of gray-scale images to address the challenge of malware identification and classification.…”

Section: B Malware Classificationmentioning

confidence: 99%

A Novel Method for Detecting Future Generations of Targeted and Metamorphic Malware Based on Genetic Algorithm

Javaheri

Lalbakhsh²,

Hosseinzadeh

2021

IEEE Access

View full text Add to dashboard Cite

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. To provide sufficient training data for malware behavioral modeling, genetic algorithms are used together with an optimization strategy that selectively creates generations of mutated elite malware samples. In our unique method, a sequence of system API calls is extracted using tracker filter drivers in a sandbox environment. The most obfuscated and metamorphic malware are chosen by an elite selection method. The behavioral chromosomes are formed by mapping extracted APIs to genes using linear regression. Our analysis system includes an Internet simulator and a human emulator to deceive intelligent classes of malware to successfully execute themselves and prevent system halting. The evolution process is performed through crossover and permutation of genes, which are encoded based on the addresses of the kernel-level system functions. An objective function has been defined to optimize the vital indicators of malignancy and tracking rate with a linear time complexity. This guarantees that new generations of malware are more destructive and stealthy than their parents. J48 and deep neural networks were employed in our experiments as they are two popular modeling and classification strategies in the area of behavioral malware detection. Real-world malware samples from valid references were used for the performance evaluation of our approach. Comprehensive scenarios were involved in the experiments to evaluate the performance of our proposed strategy. The results demonstrate significant improvement in detection accuracy -up to 5% considering rare and metamorphic malware. The results also demonstrated a considerable enhancement in true positive rate for the proposed deep-learning algorithm.

show abstract

Section: B Malware Classificationmentioning

confidence: 99%

A Novel Method for Detecting Future Generations of Targeted and Metamorphic Malware Based on Genetic Algorithm

Javaheri

Lalbakhsh²,

Hosseinzadeh

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Khan et al [49,50] analysed ResNet and GoogleNet models for malware detection using image processing technique. Kumar et al [51,52] used the Convolutional Neural Network CNN model for malicious code detection based on pattern recognition and permission-induced risk for Android IoT Devices, respectively. Comparison of the different approaches for botnet identification is a difficult task because different evaluations and experiments use different botnet samples and data sets.…”

Section: Comparison With Other Machine Learning Classifiersmentioning

confidence: 99%

An Adaptive Multi-Layer Botnet Detection Technique Using Machine Learning Classifiers

et al. 2019

Self Cite

View full text Add to dashboard Cite

In recent years, the botnets have been the most common threats to network security since it exploits multiple malicious codes like a worm, Trojans, Rootkit, etc. The botnets have been used to carry phishing links, to perform attacks and provide malicious services on the internet. It is challenging to identify Peer-to-peer (P2P) botnets as compared to Internet Relay Chat (IRC), Hypertext Transfer Protocol (HTTP) and other types of botnets because P2P traffic has typical features of the centralization and distribution. To resolve the issues of P2P botnet identification, we propose an effective multi-layer traffic classification method by applying machine learning classifiers on features of network traffic. Our work presents a framework based on decision trees which effectively detects P2P botnets. A decision tree algorithm is applied for feature selection to extract the most relevant features and ignore the irrelevant features. At the first layer, we filter non-P2P packets to reduce the amount of network traffic through well-known ports, Domain Name System (DNS). query, and flow counting. The second layer further characterized the captured network traffic into non-P2P and P2P. At the third layer of our model, we reduced the features which may marginally affect the classification. At the final layer, we successfully detected P2P botnets using decision tree Classifier by extracting network communication features. Furthermore, our experimental evaluations show the significance of the proposed method in P2P botnets detection and demonstrate an average accuracy of 98.7%.

show abstract

“…It randomly separated 10% samples for testing from malware family. Reference [34] designed a deep learning model for malware detection. The proposed approach achieved 98% classification accuracy for 9339 malware samples.…”

Section: Literature Reviewmentioning

confidence: 99%

Cyber Security Threats Detection in Internet of Things Using Deep Learning Approach

et al. 2019

View full text Add to dashboard Cite

The IoT (Internet of Things) connect systems, applications, data storage, and services that may be a new gateway for cyber-attacks as they continuously offer services in the organization. Currently, software piracy and malware attacks are high risks to compromise the security of IoT. These threats may steal important information that causes economic and reputational damages. In this paper, we have proposed a combined deep learning approach to detect the pirated software and malware-infected files across the IoT network. The TensorFlow deep neural network is proposed to identify pirated software using source code plagiarism. The tokenization and weighting feature methods are used to filter the noisy data and further, to zoom the importance of each token in terms of source code plagiarism. Then, the deep learning approach is used to detect source code plagiarism. The dataset is collected from Google Code Jam (GCJ) to investigate software piracy. Apart from this, the deep convolutional neural network is used to detect malicious infections in IoT network through color image visualization. The malware samples are obtained from Maling dataset for experimentation. The experimental results indicate that the classification performance of the proposed solution to measure the cybersecurity threats in IoT are better than the state of the art methods. INDEX TERMS Internet of Things, data mining, cyber security, software piracy, malware detection.

show abstract

Malicious Code Detection based on Image Processing Using Deep Learning

Cited by 46 publications

References 7 publications

A Novel Method for Detecting Future Generations of Targeted and Metamorphic Malware Based on Genetic Algorithm

A Novel Method for Detecting Future Generations of Targeted and Metamorphic Malware Based on Genetic Algorithm

An Adaptive Multi-Layer Botnet Detection Technique Using Machine Learning Classifiers

Cyber Security Threats Detection in Internet of Things Using Deep Learning Approach

Contact Info

Product

Resources

About