The duplication issue within the Drebin dataset
The duplication issue within the Drebin dataset
Paul Irolla,Alexandre Dey
2018 · DOI: 10.1007/s11416-018-0316-z
Journal of Computer Virology and Hacking Techniques · 30 Citations
TLDR
The Drebin dataset is discovered that 49.35% of samples in this dataset has at least one other sample that is a repackaged version containing exactly the same sequence of opcode.