Windows and IoT malware visualization and classification with deep CNN and Xception CNN using Markov images

Sharma, Osho; Sharma, Akashdeep; Kalia, Arvind

doi:10.1007/s10844-022-00734-4

Cited by 7 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the computation cost for constructing Bi-LSTM is higher than the proposed method. The framework of Sharma, Sharma & Kalia (2022) generated a better outcome; however, the computation cost is higher than the proposed MD framework. Falana et al (2022) framework comprised a CNN and generative neural network for classifying the malware images.…”

Section: Discussionmentioning

confidence: 90%

“…The proposed framework reaches the AU-ROC and AU-PRC of 0.97 and 0.84, respectively. In contrast, the remaining frameworks achieve the AU-ROC and AU-PRC of Jian et al (2021) (0.92 and 0.77), Sharma, Sharma & Kalia (2022) (0.90 and 0.81), Falana et al (2022) (0.92 and 0.73), and Vasan et al (2020) (0.78 and 0.76), accordingly.…”

Section: Resultsmentioning

confidence: 97%

“…The proposed framework achieves AU-ROC and AU-PRC values of 0.98 and 0.85, respectively. On the other hand, the AU-ROC and AU-PRC values of Jian et al (2021) (0.88 and 0.75), Sharma, Sharma & Kalia (2022) (0.89 and 0.77), Falana et al (2022) (0.87 and 0.69) and Vasan et al (2020) (0.84 and 0.74), accordingly. The outcome represents the classification efficiency of the proposed MD.…”

Section: Resultsmentioning

confidence: 98%

“…The proposed model is implemented in Windows 10 professional environment, i7 processor, GTX 1080 Ti (11 GB). Python 3.9 with Keras ( Keras, 2022 ) library is employed for developing the proposed framework, Vasan et al (2020) framework, Jian et al (2021) framework, Sharma, Sharma & Kalia (2022) framework, and Falana et al (2022) framework. In addition, YoloV7 ( Wang, Bochkovskiy & Liao, 2022 ), DenseNet161 ( DenseNet161, 2022 ) and HHO ( HHO, 2022 ) are utilized for constructing the model.…”

Section: Resultsmentioning

confidence: 99%

“…Similarly, Sharma, Sharma & Kalia (2022) proposed an Xception CNN-based MD framework for classifying malware images. The authors stated that the models achieve a superior outcome than the current frameworks.…”

Section: Literature Reviewmentioning

confidence: 99%

See 4 more Smart Citations

Artificial intelligence-driven malware detection framework for internet of things environment

Alsubai

Dutta²,

Alnajim

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

The Internet of Things (IoT) environment demands a malware detection (MD) framework for protecting sensitive data from unauthorized access. The study intends to develop an image-based MD framework. The authors apply image conversion and enhancement techniques to convert malware binaries into RGB images. You only look once (Yolo V7) is employed for extracting the key features from the malware images. Harris Hawks optimization is used to optimize the DenseNet161 model to classify images into malware and benign. IoT malware and Virusshare datasets are utilized to evaluate the proposed framework’s performance. The outcome reveals that the proposed framework outperforms the current MD framework. The framework generates the outcome at an accuracy and F1-score of 98.65 and 98.5 and 97.3 and 96.63 for IoT malware and Virusshare datasets, respectively. In addition, it achieves an area under the receiver operating characteristics and the precision-recall curve of 0.98 and 0.85 and 0.97 and 0.84 for IoT malware and Virusshare datasets, accordingly. The study’s outcome reveals that the proposed framework can be deployed in the IoT environment to protect the resources.

show abstract

Section: Discussionmentioning

confidence: 90%