Comparison of Three Deep Learning-based Approaches for IoT Malware Detection

Nguyen, Khanh; Tuan, Tran Minh; Le, Son Hai; Viet, Anh; Ogawa, Mizuhito; Minh, Nguyen Le

doi:10.1109/kse.2018.8573374

Cited by 21 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nguyen et al [40] proposed "BE-PUM" -Binary code analyzer based on dynamic symbolic execution on x86that overcomes obfuscation for precise malware disassembly. IoT malwares do not employ obfuscation as frequently as PC malware.…”

Section: Discussion On Surveyed Papersmentioning

confidence: 99%

“…Allows data recovery and reverse engineering hexedit -Helps to view/edit files in hex or ASCII IDAPro [28], [18], [34], [35], [36], [30] Prominently used interactive disassembler and debugger tool magic -file command's magic pattern file nucleus [28] A structural control flow graph analysis based compiler agnostic function detection tool for binaries proposed by Andriesse et al [37]. obj(ect)dump [38], [39], [40] Information dump about object files including intended target instruction set architecture (ISA) and structural information. Relies on BFD.…”

Section: Elfdump -mentioning

confidence: 99%

“…The encoding of text information in the actual binary is often overlooked, and a default encoding of UTF-8 is assumed. Several models work well under this assumption for Windows [65], [66], [67], and Linux [40] platforms, yet the effect of considering the actual encoding is largely unexplored.…”

Section: Sequence-based Featuresmentioning

confidence: 99%

“…instruction sequences, or simply the whole file [21]. Various entropy measures are available such as Shannon entropy [40].…”

Section: C: Entropy Sequencementioning

confidence: 99%

“…Both recommendations are provided in Tables 5 and 6. It is an extension of the grayscale representation described above, where conversion to a colored format is done by extending grayscale values to RGB channel values using tools like BinVis 1 , as done by Nguyen et al in [40].…”

Section: C: Entropy Sequencementioning

confidence: 99%

See 4 more Smart Citations

A Survey on Cross-Architectural IoT Malware Threat Hunting

et al. 2021

View full text Add to dashboard Cite

In recent years, the increase in non-Windows malware threats had turned the focus of the cybersecurity community. Research works on hunting Windows PE-based malwares are maturing, whereas the developments on Linux malware threat hunting are relatively scarce. With the advent of the Internet of Things (IoT) era, smart devices that are getting integrated into human life have become a hackers' highway for their malicious activities. The IoT devices employ various Unix-based architectures that follow ELF (Executable and Linkable Format) as their standard binary file specification. This study aims at providing a comprehensive survey on the latest developments in cross-architectural IoT malware detection and classification approaches. Aided by a modern taxonomy, we discuss the feature representations, feature extraction techniques, and machine learning models employed in the surveyed works. We further provide more insights on the practical challenges involved in cross-architectural IoT malware threat hunting and discuss various avenues to instill potential future research.

show abstract

Section: Discussion On Surveyed Papersmentioning

confidence: 99%