按年被提到
20152016 · 2 次2026
AI 安全、伦理与社会影响›对抗样本与后门·arXiv:1511.06292 · cs.LG

Foveation-based Mechanisms Alleviate Adversarial Examples

Yan Luo, Xavier Boix, Gemma Roig, Tomaso Poggio, Qi Zhao · 2015
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2016-05-10 · 最近 2016-07-06
2不同的人
2活跃月份
2讨论串
128被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We show that adversarial examples, i.e., the visually imperceptible perturbations that result in Convolutional Neural Networks (CNNs) fail, can be alleviated with a mechanism based on foveations---applying the CNN in different image regions. To see this, first, we report results in ImageNet that lead to a revision of the hypothesis that adversarial perturbations are a consequence of CNNs acting as a linear classifier: CNNs act locally linearly to changes in the image regions with objects recognized by the CNN, and in other regions the CNN may act non-linearly. Then, we corroborate that when the neural responses are linear, applying the foveation mechanism to the adversarial example tends to significantly reduce the effect of the perturbation. This is because, hypothetically, the CNNs for ImageNet are robust to changes of scale and translation of the object produced by the foveation, but this property does not generalize to transformations of the perturbation. As a result, the accuracy after a foveation is almost the same as the accuracy of the CNN without the adversarial perturbation, even if the adversarial perturbation is calculated taking into account a foveation.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论argonaut · 2016-05

“Are you referring to this foveation paper (http://arxiv.org/abs/1511.06292)? I'm quite skeptical of the claims in that paper; upon closer reading their experiments are problematic. Also, it appears the paper was rejected. I can elaborate if that is indeed the case.”

End to End Learning for Self-Driving Cars [pdf]原评论 ↗
被提交为 story · 1 次