Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets than those required for standard classification. This result is a key hurdle in the deployment of robust machine learning models in many real world applications where labeled data is expensive. Our main insight is that unlabeled data can be a competitive alternative to labeled data for training adversarially robust models. Theoretically, we show that in a simple statistical setting, the sample complexity for learning an adversarially robust model from unlabeled data matches the fully supervised case up to constant factors. On standard datasets like CIFAR-10, a simple Unsupervised Adversarial Training (UAT) approach using unlabeled data improves robust accuracy by 21.7% over using 4K supervised examples alone, and captures over 95% of the improvement from the same number of labeled examples. Finally, we report an improvement of 4% over the previous state-of-the-art on CIFAR-10 against the strongest known attack by using additional unlabeled data from the uncurated 80 Million Tiny Images dataset. This demonstrates that our finding extends as well to the more realistic case where unlabeled data is also uncurated, therefore opening a new avenue for improving adversarial training.

研究表明，使用未标记的数据进行训练可以作为对于耐受对抗攻击模型的有竞争力的替代方法，具体而言是在简单的统计情况下，学习对抗鲁棒模型的样本复杂度与完全受监督的情况一致。此外，使用未标记数据的无监督对抗训练方法可以在 CIFAR-10 这样的标准数据集上，使得鲁棒准确性比仅仅使用 4K 监督样例有 21.7% 的提升，并且可以捕捉到相同数量标记样例的改进量中超过 95% 的部分。最后，使用来自未筛选的 8000 万张小图片数据集的额外未标记数据，在 CIFAR-10 上击败了当前已知最强的攻击，展示了我们的发现也适用于未筛选的现实情况，从而为提高对抗训练打开了新的途径。

标签是否需要以提高对抗性鲁棒性？