A law of adversarial risk, interpolation, and label noise. (arXiv:2207.03933v1 [stat.ML])

In supervised learning, it has been shown that label noise in the data can be
interpolated without penalties on test accuracy under many circumstances. We
show that interpolating label noise induces adversarial vulnerability, and
prove the first theorem showing the dependence of label noise and adversarial
risk in terms of the data distribution. Our results are almost sharp without
accounting for the inductive bias of the learning algorithm. We also show that
inductive bias makes the effect of label noise …

adversarial law ml risk