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

Malware represents a significant security concern in today's digitallandscape, as it can destroy or disable operating systems, steal sensitive userinformation, and occupy valuable disk space. However, current malware detectionmethods, such as static-based and dynamic-based approaches, struggle toidentify newly developed (``zero-day") malware and are limited by customizedvirtual machine (VM) environments. To overcome these limitations, we propose anovel malware detection approach that leverages deep learning, mathematicaltechniques, and network science. Our approach focuses on static and dynamicanalysis and utilizes the Low-Level Virtual Machine (LLVM) to profileapplications within a complex network. The generated network topologies areinput into the GraphSAGE architecture to efficiently distinguish between benignand malicious software applications, with the operation names denoted as nodefeatures. Importantly, the GraphSAGE models analyze the network's topologicalgeometry to make predictions, enabling them to detect state-of-the-art malwareand prevent potential damage during execution in a VM. To evaluate ourapproach, we conduct a study on a dataset comprising source code from 24,376applications, specifically written in C/C++, sourced directly fromwidely-recognized malware and various types of benign software. The resultsshow a high detection performance with an Area Under the Receiver OperatingCharacteristic Curve (AUROC) of 99.85%. Our approach marks a substantialimprovement in malware detection, providing a notably more accurate andefficient solution when compared to current state-of-the-art malware detectionmethods.

Discovering Malicious Signatures in Software from Structural Interactions