Picking on the family: Disrupting android malware triage by forcing misclassification

作者：

Highlights：

• We propose IagoDroid, a novel evasion attack against static analysis.

• IagoDroid successfully swaps the classification of 28 of 29 malware families.

• IagoDroid can defeat the classifier modifying only a single feature.

• Our countermeasure detects potential evasions between 90% and 99%.

• IagoDroid and all the data used in the paper are publicly available.

摘要

•We propose IagoDroid, a novel evasion attack against static analysis.•IagoDroid successfully swaps the classification of 28 of 29 malware families.•IagoDroid can defeat the classifier modifying only a single feature.•Our countermeasure detects potential evasions between 90% and 99%.•IagoDroid and all the data used in the paper are publicly available.

论文关键词：Malware classification,Adversarial learning,Genetic algorithms,Iagodroid

论文评审过程：Received 31 March 2017, Revised 29 October 2017, Accepted 14 November 2017, Available online 15 November 2017, Version of Record 14 December 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.032