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 is being increasingly threatening and malware detectors based ontraditional signature-based analysis are no longer suitable for current malwaredetection. Recently, the models based on machine learning (ML) are developedfor predicting unknown malware variants and saving human strength. However,most of the existing ML models are black-box, which made their pre-dictionresults undependable, and therefore need further interpretation in order to beeffectively deployed in the wild. This paper aims to examine and categorize theexisting researches on ML-based malware detector interpretability. We firstgive a detailed comparison over the previous work on common ML modelinter-pretability in groups after introducing the principles, attributes,evaluation indi-cators and taxonomy of common ML interpretability. Then weinvestigate the interpretation methods towards malware detection, by addressingthe importance of interpreting malware detectors, challenges faced by thisfield, solutions for migitating these challenges, and a new taxonomy forclassifying all the state-of-the-art malware detection interpretability work inrecent years. The highlight of our survey is providing a new taxonomy towardsmalware detection interpreta-tion methods based on the common taxonomysummarized by previous re-searches in the common field. In addition, we are thefirst to evaluate the state-of-the-art approaches by interpretation methodattributes to generate the final score so as to give insight to quantifying theinterpretability. By concluding the results of the recent researches, we hopeour work can provide suggestions for researchers who are interested in theinterpretability on ML-based malware de-tection models.

Towards interpreting ML-based automated malware detection models: a survey