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

Android malware detection is a significat problem that affects billions ofusers using millions of Android applications (apps) in existing markets. Thispaper proposes PetaDroid, a framework for accurate Android malware detectionand family clustering on top of static analyses. PetaDroid automatically adaptsto Android malware and benign changes over time with resilience to commonbinary obfuscation techniques. The framework employs novel techniqueselaborated on top of natural language processing (NLP) and machine learningtechniques to achieve accurate, adaptive, and resilient Android malwaredetection and family clustering. PetaDroid identifies malware using an ensembleof convolutional neural network (CNN) on proposed Inst2Vec features. Theframework clusters the detected malware samples into malware family groupsutilizing sample feature digests generated using deep neural auto-encoder. Forchange adaptation, PetaDroid leverages the detection confidence probabilityduring deployment to automatically collect extension datasets and periodicallyuse them to build new malware detection models. Besides, PetaDroid usescode-fragment randomization during the training to enhance the resiliency tocommon obfuscation techniques. We extensively evaluated PetaDroid on multiplereference datasets. PetaDroid achieved a high detection rate (98-99% f1-score)under different evaluation settings with high homogeneity in the producedclusters (96%). We conducted a thorough quantitative comparison withstate-of-the-art solutions MaMaDroid, DroidAPIMiner, MalDozer, in whichPetaDroid outperforms them under all the evaluation settings.

Resilient and Adaptive Framework for Large Scale Android Malware Fingerprinting using Deep Learning and NLP Techniques