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

With the growing pace of using Deep Learning (DL) to solve various problems,securing these models against adversaries has become one of the main concernsof researchers. Recent studies have shown that DL-based malware detectors arevulnerable to adversarial examples. An adversary can create carefully craftedadversarial examples to evade DL-based malware detectors. In this paper, wepropose Mal2GCN, a robust malware detection model that uses Function Call Graph(FCG) representation of executable files combined with Graph ConvolutionNetwork (GCN) to detect Windows malware. Since FCG representation of executablefiles is more robust than raw byte sequence representation, numerous proposedadversarial example generating methods are ineffective in evading Mal2GCN.Moreover, we use the non-negative training method to transform Mal2GCN to amonotonically non-decreasing function; thereby, it becomes theoretically robustagainst appending attacks. We then present a black-box source code-basedadversarial malware generation approach that can be used to evaluate therobustness of malware detection models against real-world adversaries. Theproposed approach injects adversarial codes into the various locations ofmalware source codes to evade malware detection models. The experimentsdemonstrate that Mal2GCN with non-negative weights has high accuracy indetecting Windows malware, and it is also robust against adversarial attacksthat add benign features to the Malware source code.

Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weights