论文标题
强大而私人学习半空间
Robust and Private Learning of Halfspaces
论文作者
论文摘要
在这项工作中，我们研究了在学习半空间的L2扰动下差异隐私与对抗性鲁棒性之间的权衡。我们证明，对于大量参数，对半空间的强大私人学习的样本复杂性几乎紧密。我们结果的一个亮点是，鲁棒和私人学习比仅靠鲁棒或私人学习要难。我们通过对MNIST和USPS数据集的实验结果进行了补充，以进行学习算法，该算法既有私密，又具有对手的稳定性。
In this work, we study the trade-off between differential privacy and adversarial robustness under L2-perturbations in the context of learning halfspaces. We prove nearly tight bounds on the sample complexity of robust private learning of halfspaces for a large regime of parameters. A highlight of our results is that robust and private learning is harder than robust or private learning alone. We complement our theoretical analysis with experimental results on the MNIST and USPS datasets, for a learning algorithm that is both differentially private and adversarially robust.
