"New Research: Machine Learning Classifiers Don't Need Negative Labels"

#1689599: "New Research: Machine Learning Classifiers Don't Need Negative Labels"

Description:	In computer security, researchers usually have easy access only to labels for malicious samples (malware, phishing domains, etc.), while labels for benign samples (productivity software, e-commerce domains, etc.) are missing entirely—or they are tedious and expensive to collect at scale. Typically, this leads to researchers regarding the “known bad” samples as malicious, while the rest is presumed to be benign. DNSFilter's Chief Data Scientist, David Elkind, recently published research that shows that this solution leads to a biased model. In this presentation, David will walk through his findings and explain how DNSFilter’s Malicious Domain Protection uses the concepts in his research to detect threats an average of 10 days sooner than other technologies. Speakers: David Elkind, Chief Data Scientist, DNSFilter David J. Elkind is the Chief Data Scientist at DNSFilter. He holds a MS in mathematics and statistics from Georgetown University. Moderator - Terry Sweeney, Moderator - Contributing Editor, Dark Reading Terry Sweeney is a Los Angeles-based writer and editor who's covered business technology for three decades. He's written about cyber security for more than 15 years and was one of the founding editors of Dark Reading. Sweeney has covered enterprise networking extensively, as well as its supporting technologies like storage, wireless, cloud-based apps and the emerging Internet of Things. He's been a contributing editor to The Washington Post, Crain’s New York Business, Red Herring, Information Week, Network World, SearchAWS.com, and Stadium Tech Report.
More info:	https://dr-resources.darkreading.com/free/w_defa8737/

Description:

In computer security, researchers usually have easy access only to labels for malicious samples (malware, phishing domains, etc.), while labels for benign samples (productivity software, e-commerce domains, etc.) are missing entirely—or they are tedious and expensive to collect at scale.

Typically, this leads to researchers regarding the “known bad” samples as malicious, while the rest is presumed to be benign.

DNSFilter's Chief Data Scientist, David Elkind, recently published research that shows that this solution leads to a biased model. In this presentation, David will walk through his findings and explain how DNSFilter’s Malicious Domain Protection uses the concepts in his research to detect threats an average of 10 days sooner than other technologies.

Speakers:

David Elkind, Chief Data Scientist, DNSFilter
David J. Elkind is the Chief Data Scientist at DNSFilter. He holds a MS in mathematics and statistics from Georgetown University.

Moderator - Terry Sweeney, Moderator - Contributing Editor, Dark Reading
Terry Sweeney is a Los Angeles-based writer and editor who's covered business technology for three decades. He's written about cyber security for more than 15 years and was one of the founding editors of Dark Reading. Sweeney has covered enterprise networking extensively, as well as its supporting technologies like storage, wireless, cloud-based apps and the emerging Internet of Things. He's been a contributing editor to The Washington Post, Crain’s New York Business, Red Herring, Information Week, Network World, SearchAWS.com, and Stadium Tech Report.

More info:

https://dr-resources.darkreading.com/free/w_defa8737/

Date added	July 1, 2025, 3:27 p.m.
Source	DarkReading
Subjects	AI/ML - Artificial Intelligence / Machine Learning / GenAI / Artificial General Intelligence - AGI - Various PodCasts / Webcast / Webinar / eSummit / Virtual Event etc.
Venue	July 16, 2025, midnight - July 16, 2025, midnight