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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Malware family classification is a significant issue with public safety andresearch implications that has been hindered by the high cost of expert labels.The vast majority of corpora use noisy labeling approaches that obstructdefinitive quantification of results and study of deeper interactions. In orderto provide the data needed to advance further, we have created the MalwareOpen-source Threat Intelligence Family (MOTIF) dataset. MOTIF contains 3,095malware samples from 454 families, making it the largest and most diversepublic malware dataset with ground truth family labels to date, nearly 3xlarger than any prior expert-labeled corpus and 36x larger than the priorWindows malware corpus. MOTIF also comes with a mapping from malware samples tothreat reports published by reputable industry sources, which both validatesthe labels and opens new research opportunities in connecting opaque malwaresamples to human-readable descriptions. This enables important evaluations thatare normally infeasible due to non-standardized reporting in industry. Forexample, we provide aliases of the different names used to describe the samemalware family, allowing us to benchmark for the first time accuracy ofexisting tools when names are obtained from differing sources. Evaluationresults obtained using the MOTIF dataset indicate that existing tasks havesignificant room for improvement, with accuracy of antivirus majority votingmeasured at only 62.10% and the well-known AVClass tool having just 46.78%accuracy. Our findings indicate that malware family classification suffers atype of labeling noise unlike that studied in most ML literature, due to thelarge open set of classes that may not be known from the sample underconsideration

MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labels