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

Recent work has shown that adversarial Windows malware samples - referred toas adversarial EXEmples in this paper - can bypass machine learning-baseddetection relying on static code analysis by perturbing relatively few inputbytes. To preserve malicious functionality, previous attacks either add bytesto existing non-functional areas of the file, potentially limiting theireffectiveness, or require running computationally-demanding validation steps todiscard malware variants that do not correctly execute in sandbox environments.In this work, we overcome these limitations by developing a unifying frameworkthat does not only encompass and generalize previous attacks againstmachine-learning models, but also includes three novel attacks based onpractical, functionality-preserving manipulations to the Windows PortableExecutable (PE) file format. These attacks, named Full DOS, Extend and Shift,inject the adversarial payload by respectively manipulating the DOS header,extending it, and shifting the content of the first section. Our experimentalresults show that these attacks outperform existing ones in both white-box andblack-box scenarios, achieving a better trade-off in terms of evasion rate andsize of the injected payload, while also enabling evasion of models that havebeen shown to be robust to previous attacks. To facilitate reproducibility ofour findings, we open source our framework and all the corresponding attackimplementations as part of the secml-malware Python library. We conclude thiswork by discussing the limitations of current machine learning-based malwaredetectors, along with potential mitigation strategies based on embedding domainknowledge coming from subject-matter experts directly into the learningprocess.

Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection