Adversarial Robustness
Florian and Tim discuss the interplay between adversarial robustness and adversarial examples, highlighting the challenges of generalization and feature learning in machine learning models. They delve into the trade-offs between defending against perturbations and maintaining model accuracy, emphasizing the importance of deploying models with optimal average case accuracy in the face of motivated adversaries.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#040 - Adversarial Examples (Dr. Nicholas Carlini, Dr. Wieland Brendel, Florian Tramèr)
Related Questions