当前位置:
X-MOL 学术
›
arXiv.cs.LG
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Biologically Inspired Mechanisms for Adversarial Robustness
arXiv - CS - Machine Learning Pub Date : 2020-06-29 , DOI: arxiv-2006.16427 Manish V. Reddy, Andrzej Banburski, Nishka Pant, Tomaso Poggio
arXiv - CS - Machine Learning Pub Date : 2020-06-29 , DOI: arxiv-2006.16427 Manish V. Reddy, Andrzej Banburski, Nishka Pant, Tomaso Poggio
A convolutional neural network strongly robust to adversarial perturbations
at reasonable computational and performance cost has not yet been demonstrated.
The primate visual ventral stream seems to be robust to small perturbations in
visual stimuli but the underlying mechanisms that give rise to this robust
perception are not understood. In this work, we investigate the role of two
biologically plausible mechanisms in adversarial robustness. We demonstrate
that the non-uniform sampling performed by the primate retina and the presence
of multiple receptive fields with a range of receptive field sizes at each
eccentricity improve the robustness of neural networks to small adversarial
perturbations. We verify that these two mechanisms do not suffer from gradient
obfuscation and study their contribution to adversarial robustness through
ablation studies.
中文翻译:
对抗鲁棒性的生物学启发机制
尚未证明卷积神经网络在合理的计算和性能成本下对对抗性扰动具有很强的鲁棒性。灵长类视觉腹侧流似乎对视觉刺激中的小扰动具有鲁棒性,但引起这种强烈感知的潜在机制尚不清楚。在这项工作中,我们研究了两种生物学上合理的机制在对抗鲁棒性中的作用。我们证明了灵长类动物视网膜执行的非均匀采样以及在每个偏心率处具有一系列感受野大小的多个感受野的存在提高了神经网络对小的对抗性扰动的鲁棒性。
更新日期:2020-07-01
中文翻译:
对抗鲁棒性的生物学启发机制
尚未证明卷积神经网络在合理的计算和性能成本下对对抗性扰动具有很强的鲁棒性。灵长类视觉腹侧流似乎对视觉刺激中的小扰动具有鲁棒性,但引起这种强烈感知的潜在机制尚不清楚。在这项工作中,我们研究了两种生物学上合理的机制在对抗鲁棒性中的作用。我们证明了灵长类动物视网膜执行的非均匀采样以及在每个偏心率处具有一系列感受野大小的多个感受野的存在提高了神经网络对小的对抗性扰动的鲁棒性。