L(a)ying in (Test)Bed - How Biased Datasets Produce Impractical Results for Actual Malware Families' Classification
L(a)ying in (Test)Bed - How Biased Datasets Produce Impractical Results for Actual Malware Families' Classification
Tamy Beppler,Marcus Botacin,2 Authors,A. Grégio
2019 · DOI: 10.1007/978-3-030-30215-3_19
Information Security Conference · 18 Citations
TLDR
Tests with a broader unfiltered dataset show that texture analysis may be impractical for correct malware classification in a real world scenario, in which there is a great variety of families and some of them make use of quite sophisticate obfuscation techniques.