论文标题
减少对抗性的学习
Reducing Adversarially Robust Learning to Non-Robust PAC Learning
论文作者
论文摘要
我们研究了将对抗性鲁棒性学习减少到标准PAC学习的问题，即仅使用黑框非稳定学习者访问的对手稳健的预测指标的复杂性。我们提供的减少可以使用任何非固定学习者$ \ Mathcal {a} $ for $ \ MATHCAL {C} $使用任何非固定学习者$ \ Mathcal {a} $。 $ \ Mathcal {a} $的调用数取决于对数取决于允许的对抗扰动的数量，并且我们给出一个下限，显示这是不可避免的。
We study the problem of reducing adversarially robust learning to standard PAC learning, i.e. the complexity of learning adversarially robust predictors using access to only a black-box non-robust learner. We give a reduction that can robustly learn any hypothesis class $\mathcal{C}$ using any non-robust learner $\mathcal{A}$ for $\mathcal{C}$. The number of calls to $\mathcal{A}$ depends logarithmically on the number of allowed adversarial perturbations per example, and we give a lower bound showing this is unavoidable.
