Vulnerabilities & Threats

How Bad Teachers Ruin Good Machine Learning

Sophos data scientist Hillary Sanders explains how security suffers when good machine learning models are trained on bad testing data.

Sara Peters, Senior Editor

August 18, 2017

Read more about:

About the Author

Sara Peters

Sara Peters

Senior Editor

Sara Peters is Senior Editor at Dark Reading and formerly the editor-in-chief of Enterprise Efficiency. Prior that she was senior editor for the Computer Security Institute, writing and speaking about virtualization, identity management, cybersecurity law, and a myriad of other topics. She authored the 2009 CSI Computer Crime and Security Survey and founded the CSI Working Group on Web Security Research Law -- a collaborative project that investigated the dichotomy between laws regulating software vulnerability disclosure and those regulating Web vulnerability disclosure.

See more from Sara Peters

You May Also Like

More Insights

Webinars

How to Evaluate Hybrid-Cloud Network Policies and Enhance Security
Sep 18, 2024
DORA and PCI DSS 4.0: Scale Your Mainframe Security Strategy Among Evolving Regulations
Sep 26, 2024
Harnessing the Power of Automation to Boost Enterprise Cybersecurity
Oct 3, 2024
10 Emerging Vulnerabilities Every Enterprise Should Know
Oct 30, 2024

Events

State of AI in Cybersecurity: Beyond the Hype
Oct 30, 2024
[Virtual Event] The Essential Guide to Cloud Management
Oct 17, 2024
Black Hat Europe - December 9-12 - Learn More
Dec 10, 2024
SecTor - Canada's IT Security Conference Oct 22-24 - Learn More
Oct 22, 2024