English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Adversarial machine learning in the context of image processing and relatedapplications has received a large amount of attention. However, adversarialmachine learning, especially adversarial deep learning, in the context ofmalware detection has received much less attention despite its apparentimportance. In this paper, we present a framework for enhancing the robustnessof Deep Neural Networks (DNNs) against adversarial malware samples, dubbedHashing Transformation Deep Neural Networks} (HashTran-DNN). The core idea isto use hash functions with a certain locality-preserving property to transformsamples to enhance the robustness of DNNs in malware classification. Theframework further uses a Denoising Auto-Encoder (DAE) regularizer toreconstruct the hash representations of samples, making the resulting DNNclassifiers capable of attaining the locality information in the latent space.We experiment with two concrete instantiations of the HashTran-DNN framework toclassify Android malware. Experimental results show that four known attacks canrender standard DNNs useless in classifying Android malware, that knowndefenses can at most defend three of the four attacks, and that HashTran-DNNcan effectively defend against all of the four attacks.

HashTran-DNN: A Framework for Enhancing Robustness of Deep Neural Networks against Adversarial Malware Samples