At DEF CON 24, we caught up with speaker Clarence Chio to discuss his research and current project dealing with adversarial machine learning and machine learning vulnerabilities.

Clarence gives our host, Alicia Webb, a hacking demo involving an image classification engine and the issues it has once a noise vector is added. He also informs us of his open source project, Deep- Pwning ‘Metaspolit for Machine Learning’ which allows you to generate noise vectors in hopes that people will continue to test machine learning vulnerabilities and build upon the outcome.

Deep- Pwning on GitHub:

Stay tuned for lots more coverage from Def Con 24 in Las Vegas.

Leave us a comment to let us know what you thought of this video with Zulfikar!

SUBSCRIBE to SecureNinjaTV to catch weekly episodes of..
+ Hacking Demos
+ Cybersecurity Discussions
+ Tech Trade Show Coverage From Around The World

If you are in need of Cybersecurity training head over to for onsite or classroom course options.

Snapchat/ SecureNinja

Jon’s Channel:
Alicia’s Channel: