Malware Classification with Improved Convolutional Neural Network Model

Lad, Sumit S.; Adamuthe, Amol C.

doi:10.5815/ijcnis.2020.06.03

Cited by 17 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed model generated a vector of 256 neurons with the fully connected layer, which is input to SVM. The proposed model achieved 98.03% accuracy, which is better than the accuracy rates of other CNN models, such as Xception (97.56%), InceptionV3 (97.22%), and VGG16 (96.96%) [30].…”

Section: Related Workmentioning

confidence: 79%

New Approach to Malware Detection Using Optimized Convolutional Neural Network

Omar

2022

Machine Learning for Cybersecurity

View full text Add to dashboard Cite

Cyber-crimes have become a multi-billion-dollar industry in the recent years. Most cybercrimes/attacks involve deploying some type of malware. Malware that viciously targets every industry, every sector, every enterprise and even individuals has shown its capabilities to take entire business organizations offline and cause significant financial damage in billions of dollars annually.Malware authors are constantly evolving in their attack strategies and sophistication and are developing malware that is difficult to detect and can lay dormant in the background for quite some time in order to evade security controls. Given the above argument, Traditional approaches to malware detection are no longer effective. As a result, deep learning models have become an emerging trend to detect and classify malware. This paper proposes a new convolutional deep learning neural network to accurately and effectively detect malware with high precision. This paper is different than most other papers in the literature in that it uses an expert data science approach by developing a convolutional neural network from scratch to establish a baseline of the performance model first, explores and implements an improvement model from the baseline model, and finally it evaluates the performance of the final model.The baseline model initially achieves 98% accurate rate but after increasing the depth of the CNN model, its accuracy reaches 99.183 which outperforms most of the CNN models in the literature. Finally, to further solidify the effectiveness of this CNN model, we use the improved model to make predictions on new malware samples within our dataset.

show abstract

Section: Related Workmentioning

confidence: 79%

New Approach to Malware Detection Using Optimized Convolutional Neural Network

Omar

2022

Machine Learning for Cybersecurity

View full text Add to dashboard Cite

show abstract

“…Also, subsequent research will delve into using other existing optimization algorithm that are yet to be exploited by other researchers in the design and optimization of both FIR and IIR digital filters. These algorithms include Least Square Support Vector Machine (LS-SVM) [26], k-Nearest Neighbor [27], hybrid of decision tree and genetic algorithm [28], hybrid of Fuzzy logic and Convolution Neural Network (CNN) [29], and hybrid CNN and SVM model [30].…”

Section: Discussionmentioning

confidence: 99%

Moth Flame Optimization Algorithm for Optimal FIR Filter Design

Adamu¹,

Dada²,

Bassi³

2021

IJISA

View full text Add to dashboard Cite

This paper presents the application of Moth Flame optimization (MFO) algorithm to determine the best impulse response coefficients of FIR low pass, high pass, band pass and band stop filters. MFO was inspired by observing the navigation strategy of moths in nature called transverse orientation composed of three mathematical submodels. The performance of the proposed technique was compared to those of other well-known high performing optimization techniques like techniques like Particle Swarm Optimization (PSO), Novel Particle Swarm Optimization (NPSO), Improved Novel Particle Swarm Optimization (INPSO), Genetic Algorithm (GA), Parks and McClellan (PM) Algorithm. The performances of the MFO based designed optimized FIR filters have proved to be superior as compared to those obtained by PSO, NPSO, INPSO, GA, and PM Algorithm. Simulation results indicated that the maximum stop band ripples 0.057326, transition width 0.079 and fitness value 1.3682 obtained by MFO is better than that of PSO, NPSO, INPSO, GA, and PM Algorithms. The value of stop band ripples indicated the ripples or fluctuations obtained at the range which signals are attenuated is very low. The reduced value of transition width is the rate at which a signal changes from either stop band to pass band of a filter or vice versa is very good. Also, small fitness value in an indication that the values of the control variable of MFO are very near to its optimum solutions. The proposed design technique in this work generates excellent solution with high computational efficiency. This shows that MFO algorithm is an outstanding technique for FIR filter design.

show abstract

“…Natraj et al [14] 98.08 ---Cui et al [35] 94.50 -0.9460 0.9450 LGMP-2018 (encoder based) [36] 90.23 ---LGMP-2018 (cluster based) [36] 89.58 ---NSGA-II [37] 97.60 --0.8840 VGG, end-to-end [38] 90.77 ---VGG, SVM [38] 92.29 ---S. Lad et al (CNN + SVM) [39] 98.03 ---Proposed DBFS-MC 98.61 0.9632 0.9627 0.9630…”

Section: Technique %Accuracy F-score Precision Recallmentioning

confidence: 99%

Detection of Exceptional Malware Variants Using Deep Boosted Feature Spaces and Machine Learning

et al. 2021

View full text Add to dashboard Cite

Malware is a key component of cyber-crime, and its analysis is the first line of defence against cyber-attack. This study proposes two new malware classification frameworks: Deep Feature Space-based Malware classification (DFS-MC) and Deep Boosted Feature Space-based Malware classification (DBFS-MC). In the proposed DFS-MC framework, deep features are generated from the customized CNN architectures and are fed to a support vector machine (SVM) algorithm for malware classification, while, in the DBFS-MC framework, the discrimination power is enhanced by first combining deep feature spaces of two customized CNN architectures to achieve boosted feature spaces. Further, the detection of exceptional malware is performed by providing the deep boosted feature space to SVM. The performance of the proposed malware classification frameworks is evaluated on the MalImg malware dataset using the hold-out cross-validation technique. Malware variants like Autorun.K, Swizzor.gen!I, Wintrim.BX and Yuner.A is hard to be correctly classified due to their minor inter-class differences in their features. The proposed DBFS-MC improved performance for these difficult to discriminate malware classes using the idea of feature boosting generated through customized CNNs. The proposed classification framework DBFS-MC showed good results in term of accuracy: 98.61%, F-score: 0.96, precision: 0.96, and recall: 0.96 on stringent test data, using 40% unseen data.

show abstract

Malware Classification with Improved Convolutional Neural Network Model

Cited by 17 publications

References 40 publications

New Approach to Malware Detection Using Optimized Convolutional Neural Network

New Approach to Malware Detection Using Optimized Convolutional Neural Network

Moth Flame Optimization Algorithm for Optimal FIR Filter Design

Detection of Exceptional Malware Variants Using Deep Boosted Feature Spaces and Machine Learning

Contact Info

Product

Resources

About