File(s) not publicly available

Selective adversarial learning for mobile malware

conference contribution
posted on 30.10.2019, 00:00 authored by ME Khoda, Tasadduq ImamTasadduq Imam, J Kamruzzaman, I Gondal, A Rahman
Machine learning models, including deep neural networks, have been shown to be vulnerable to adversarial attacks. Adversarial samples are crafted from legitimate inputs by carefully introducing small perturbation to the input so that the classifier is fooled. Adversarial retraining, which involves retraining the classifier using adversarial samples, has been shown to improve the robustness of the classifier against adversarial attacks. However, it has been also shown that retraining with too many samples can lead to performance degradation. Hence, a careful selection of the adversarial samples that are used to retrain the classifier is necessary, yet existing works select these samples in a randomized fashion. In our work, we propose two novel approaches for selecting adversarial samples: based on the distance from cluster center of malware and based on the probability derived from a kernel based learning (KBL). Our experiment results show that both of our selective mechanisms for adversarial retraining outperform the random selection technique and significantly improve the classifier performance against adversarial attacks. In particular, selection with KBL delivers above 6% improvement in detection accuracy compared to random selection. The method proposed here has greater impact in designing robust machine learning system for security applications.

Funding

Other

History

Start Page

272

End Page

279

Number of Pages

8

Start Date

05/08/2019

Finish Date

08/08/2019

eISSN

2324-9013

ISSN

2324-898X

ISBN-13

9781728127781

Location

Rotorua, New Zealand

Publisher

IEEE

Place of Publication

Piscataway, NJ

Peer Reviewed

Yes

Open Access

No

External Author Affiliations

Federation University, CSIRO

Era Eligible

Yes

Name of Conference

2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE)