The Application Security Podcast cover image

Rob van der Veer -- OWASP AI Security & Privacy Guide

The Application Security Podcast

00:00

Under the AI Model Attacks in the OWAS, AI Security and Privacy Guide

An attacker could somehow manipulate data into a model that would get reflected into another system somewhere downstream introducing a vulnerability. It's hard to detect also from the logic because if you look at a neural network, for example, it's just a bunch of weights. You have to test, which is why testing is so super important. But also really protecting that data pipeline makes sure that this data poisoning cannot happen.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app