Jack Fitzsimons | Evil Models: Hiding Malware in Neural NetworksWatch or listen on... Youtube PodbeanDid you know that it's possible to hide malware in neural networks? Actually, you can hide malware in many statistical models. This is the subject of two recently-published papers (aptly titled "Evil Model" & "Evil Model 2.0"). Dr. Jack Fitzsimons makes it easy to understand how this is done, using techniques that began long before computers.
Enjoy!
------------------------------
Glen Wright Colopy
DPhil Oxon
The Data & Science Podcast / LifeBell AI
------------------------------