clm_f5f2464bWe argue instead that the primary cause of neural networks’ vulnerability to adversarial perturbation is their linear nature.
arXiv 1412.6572 · stat.ML cs.LG
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.
clm_f5f2464bWe argue instead that the primary cause of neural networks’ vulnerability to adversarial perturbation is their linear nature.
clm_fea7a52eWe show that these speculative hypotheses are unnecessary.
clm_dc0badafWe show that adversarial training can provide an additional regularization benefit beyond that provided by using dropout (Srivastava et al., 2014) alone.
res_56fb76d6Its inference procedure gets good classification accuracy (an 0.88% error rate) on MNIST.
clm_ab379097To solve the problem introduced by Nguyen et al. (2014) of generating a fooling image for a particular class, we propose adding ϵ∇xp(y = i | x) to a Gaussian … (excerpt)
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1412.6572) 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.