res_e6332734Our best MNIST model achieves an accuracy of more than 89% against the strongest adversaries in our test suite.
arXiv 1706.06083 · stat.ML cs.LG cs.NE
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
res_e6332734Our best MNIST model achieves an accuracy of more than 89% against the strongest adversaries in our test suite.
res_917fe0b3Our CIFAR10 model achieves an accuracy of 46% against 2 the same adversary.
res_a993c82eFurthermore, in case of the weaker black box/transfer attacks, our MNIST and CIFAR10 networks achieve the accuracy of more than 95% and 64%, respectively.
clm_30e9cce6We argue that the loss landscape corresponding to this problem has a surprisingly tractable structure of local maxima.
clm_35432e38Surprisingly, our experiments show that the inner problemis tractable after all, at least from the perspective of first-order methods.
clm_af43039cOur experiments show that the local maxima found by PGD all have similar loss values, both for normally trained networks and adversarially trained networks.
clm_5eb54408However, our experiments suggest that such better local maxima are hard to find with first order methods: even a large number of random restarts did not find function values with … (excerpt)
clm_9b463190Despite the fact that the exact assumptions of Danskin’s theorem do not hold for our problem (the function is not continuously differentiable due to ReLU and max-pooling units, and we … (excerpt)
res_4a8b9a26We need to also argue that the value of the problem (i.e. the final loss we 8 achieve against adversarial examples) is small, thus providing guarantees for the performance of … (excerpt)
res_87218bfaThis network can achieve an accuracy of 95.2% when trained with natural examples.
res_65139fdfThese plots illustrate that we can consistently reduce the value of the inner problem of the saddle point formulation (2.1), thus producing an increasingly robust classifier. trained with natural examples, … (excerpt)
clm_c837fc79For the MNIST dataset, our networks are very robust, achieving high accuracy for a wide range of powerful 𝓁∞-bound adversaries and large perturbations.
clm_c1c8720fOur experiments on CIFAR10 have not reached the same level of performance yet.
clm_c951fc87However, our results already show that our techniques lead to significant increase in the robustness of the network.
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1706.06083) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.