id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_ehr6hvkrsjbw7o6blqm2kzngf4	Ferhat Ozgur Catak	Deep learning based Sequential model for malware analysis using Windows exe API Calls	2020	23	.pdf	application/pdf	8870	1066	58	Keywords Malware analysis, Sequential models, Network security, Long-short-term memory, Deep learning based Sequential model for malware analysis using Our research is based on the analysis of API calls made by malware on the Windows We also construct malware detection models based on this dataset using the LSTM VirusTotal service, and LSTM algorithm used for our proposed malware classification API sequence dataset, which contains malware analysis information. In this study, the malware classification method was developed by using the LSTM In this study, the malware classification method was developed by using the LSTM Figure 4 LSTM classification model with Windows API calls. Single-layer LSTM models have been created that can classify 8 different types of malware. Two-layer LSTM models have been created that can classify 8 different types of malware. Table 8 shows the two layers LSTM model classification performance results.415 As expected, based on the experimental results, LSTM based malware classification model's performance418	./cache/work_ehr6hvkrsjbw7o6blqm2kzngf4.pdf	./txt/work_ehr6hvkrsjbw7o6blqm2kzngf4.txt