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/

Zendy Plus

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

Zendy Tools

Zendy Open

With the number of new mobile malware instances increasing by over 50\%annually since 2012 [24], malware embedding in mobile apps is arguably one ofthe most serious security issues mobile platforms are exposed to. Whileobfuscation techniques are successfully used to protect the intellectualproperty of apps' developers, they are unfortunately also often used bycybercriminals to hide malicious content inside mobile apps and to deceivemalware detection tools. As a consequence, most of mobile malware detectionapproaches fail in differentiating between benign and obfuscated maliciousapps. We examine the graph features of mobile apps code by building weighteddirected graphs of the API calls, and verify that malicious apps often sharestructural similarities that can be used to differentiate them from benignapps, even under a heavily "polluted" training set where a large majority ofthe apps are obfuscated. We present DaDiDroid an Android malware app detectiontool that leverages features of the weighted directed graphs of API calls todetect the presence of malware code in (obfuscated) Android apps. We show thatDaDiDroid significantly outperforms MaMaDroid [23], a recently proposed malwaredetection tool that has been proven very efficient in detecting malware in aclean non-obfuscated environment. We evaluate DaDiDroid's accuracy androbustness against several evasion techniques using various datasets for atotal of 43,262 benign and 20,431 malware apps. We show that DaDiDroidcorrectly labels up to 96% of Android malware samples, while achieving an 91%accuracy with an exclusive use of a training set of obfuscated apps.

DaDiDroid: An Obfuscation Resilient Tool for Detecting Android Malware via Weighted Directed Call Graph Modelling