Nicholas Carlini (UCB) "Adversarial Machine Learning"
Nicholas Carlini (UCB) "Adversarial Machine Learning"
Abstract: Many fundamental properties of neural networks are still not well understood. This talk studies two of these from an adversarial perspective. I begin with my main line of research and examine the apparently-fundamental susceptibility of neural networks to adversarial …
Nicholas Carlini (UCB) "Adversarial Machine Learning" Read More »