Szegedy et al. on AI
2 quotes from Szegedy et al. on the wall, 2013, newest first. Each one is verbatim and links to where it was said. Sources include arXiv / ICLR 2014.
Nonintuitive characteristics and intrinsic blind spots
Christian Szegedy of Google with coauthors including Ilya Sutskever and Ian Goodfellow, in the December 2013 paper "Intriguing properties of neural networks" (ICLR 2014) that first reported adversarial examples in deep networks.
An imperceptible non-random perturbation to a test image
Christian Szegedy of Google and coauthors describing what became known as adversarial examples, in a paper posted to arXiv in December 2013.