This Friday, we'll be discussing a fun paper about adversarial examples. "Over the past few years, adversarial examples – or inputs that have been slightly perturbed by an adversary to cause unintended behavior in machine learning systems – have received significant attention in the machine learning community. There has been much work on training models that are not vulnerable to adversarial examples... but all this research does not really confront the fundamental question: why do these adversarial examples arise in the first place?" Blog post: https://gradientscience.org/adv/ Paper: https://arxiv.org/abs/1905.02175 Summaries of paper and counterpoints: https://www.alignmentforum.org/posts/NTwA3J99RPkgmp6jh/an-62-are-adversarial... We'll meet Friday at 1. https://oregonstate.zoom.us/j/2739792686?pwd=VkRUeHJkYnhvTzlvZzR6YnZWNERKQT0... Alex Turner