TY - GEN
T1 - How Can We Craft Large-Scale Android Malware? An Automated Poisoning Attack
AU - Chen, Sen
AU - Xue, Minhui
AU - Fan, Lingling
AU - Ma, Lei
AU - Liu, Yang
AU - Xu, Lihua
N1 - Funding Information:
We appreciate the reviewers' constructive feedback. This work is partially supported by NSFC Grant 61502170, NTU Research Grant NGF-2017-03-033 and NRF Grant CRDCG2017-S04.
Funding Information:
ACKNOWLEDGMENTS We appreciate the reviewers’ constructive feedback. This work is partially supported by NSFC Grant 61502170, NTU Research Grant NGF-2017-03-033 and NRF Grant CRDCG2017-S04.
PY - 2019/3/21
Y1 - 2019/3/21
N2 - Android malware, is one of the most serious threats to mobile security. Today, machine learning-based approach is one of the most promising approaches in detecting Android malware. However, our previous experiments show that sophisticated attackers can craft large-scale Android malware to pollute training data and pose an automated poisoning attack on machine learning-based malware detection systems (e.g., Drebin, Droidapiminer, Stormdroid, and Mamadroid), and eventually mislead the detection tools. We further examine how machine learning classifiers can be mislead under four different attack models and significantly reduce detection accuracy. Apart from Android malware, to better protect mobile devices, we also discuss a general threat model of Android devices to investigate the capabilities of different attackers.
AB - Android malware, is one of the most serious threats to mobile security. Today, machine learning-based approach is one of the most promising approaches in detecting Android malware. However, our previous experiments show that sophisticated attackers can craft large-scale Android malware to pollute training data and pose an automated poisoning attack on machine learning-based malware detection systems (e.g., Drebin, Droidapiminer, Stormdroid, and Mamadroid), and eventually mislead the detection tools. We further examine how machine learning classifiers can be mislead under four different attack models and significantly reduce detection accuracy. Apart from Android malware, to better protect mobile devices, we also discuss a general threat model of Android devices to investigate the capabilities of different attackers.
UR - http://www.scopus.com/inward/record.url?scp=85064204113&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064204113&partnerID=8YFLogxK
U2 - 10.1109/AI4Mobile.2019.8672691
DO - 10.1109/AI4Mobile.2019.8672691
M3 - Conference contribution
AN - SCOPUS:85064204113
T3 - AI4Mobile 2019 - 2019 IEEE 1st International Workshop on Artificial Intelligence for Mobile
SP - 21
EP - 24
BT - AI4Mobile 2019 - 2019 IEEE 1st International Workshop on Artificial Intelligence for Mobile
A2 - Liu, Yang
A2 - Xue, Minhui
A2 - Ma, Lei
A2 - Li, Li
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st IEEE International Workshop on Artificial Intelligence for Mobile, AI4Mobile 2019
Y2 - 24 February 2019
ER -