6cfe0e6127fa25df2a0ef2ae1067d915-Paper.pdf

However,maximum-marginclassifiers areinherently robusttoperturbations ofdata at prediction time, and this implication is at odds with concrete evidence that neural networks, in practice, are brittle toadversarial examples [71]and distribution shifts [52,58,44,65]. Hence, the linear setting, while convenient to analyze, is insufficient to capture the non-robustness of neural networkstrainedonrealdatasets.Goingbeyondthelinearsetting,severalworks[ 1,49,74]arguethat neuralnetworksgeneralize wellbecause standard training procedures haveabiastowardslearning