Multimodal GANs and Adversarial Attacks
Kyle and Gokula discuss the performance of GANs under a multimodal setting and the potential challenges of producing adversarial attacks in different spaces. They highlight the strength of GANs in not requiring exposure to adversarial images during training and their ability to generalize over multiple attacks and datasets.In this clip
From this podcast
Data Skeptic
Defending Against Adversarial Attacks
Related Questions