Over a million developers have joined DZone.

Microsoft Competition: Predict Which PCs Will Get Infected With Malware

DZone 's Guide to

Microsoft Competition: Predict Which PCs Will Get Infected With Malware

The challenge? Predict how likely it is that a given machine will experience a malware attack.

· AI Zone ·
Free Resource

Microsoft recently published a blog post announcing a new competition for data scientists. It calls for participants to use machine learning to predict, given the current state of a device, when (or if) it is likely to get infected with malware.

"The competition provides academics and researchers with varied backgrounds a fresh opportunity to work on a real-world problem using a fresh set of data from Microsoft," the blog post states. "Results from the contest will help us identify opportunities to further improve Microsoft’s layered defenses, focusing on preventative protection. Not all machines are equally likely to get malware; competitors will help build models for identifying devices that have a higher risk of getting malware so that preemptive action can be taken."

Microsoft also released a 9.4GB anonymized dataset gathered from 16.8 million machines, allowing participants to test their models on real data. As of this writing, 290 teams and 304 competitors have signed up, and there are 927 entries.

The competition is open for three months, with a submission deadline of March 13, 2019. Details are available on Kaggle, where the contest is posted.

The five winning teams will receive a combined $25,000, with $12,000 going to first place, $7,000 going to second place, $3,000 going to third place, $2,000 going to fourth place, and $1,000 going to fifth place. Submission are evaluated on the size of the area under the ROC curve (receiver operating characteristic) between the prediction and the observed label.

To enter the competition, or to learn more about it, visit its page on Kaggle.

ai ,microsoft ,machine learning ,cybersecurity ,prediction ,malware

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}