Rob van der Veer -- OWASP AI Security & Privacy Guide
The Application Security Podcast
00:00
Can You Manipulate Your Training Data?
Self-driving cars are taking in images and my guess is those images are being fed back into the model at some point. Can you manipulate the model through the real world, through the valid sensors that the cars are having and maybe feeding back? Yes, you could, but you would also need to influence the labels, so the training set contained images, but also labels. However, if the training set is based on things on the internet and there's no labeling required, then things go, can go really haywire.
Transcript
Play full episode
