当前位置:
X-MOL 学术
›
arXiv.cs.NE
›
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.)
Decoder-free Robustness Disentanglement without (Additional) Supervision
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2020-07-02 , DOI: arxiv-2007.01356 Yifei Wang, Dan Peng, Furui Liu, Zhenguo Li, Zhitang Chen, Jiansheng Yang
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2020-07-02 , DOI: arxiv-2007.01356 Yifei Wang, Dan Peng, Furui Liu, Zhenguo Li, Zhitang Chen, Jiansheng Yang
Adversarial Training (AT) is proposed to alleviate the adversarial
vulnerability of machine learning models by extracting only robust features
from the input, which, however, inevitably leads to severe accuracy reduction
as it discards the non-robust yet useful features. This motivates us to
preserve both robust and non-robust features and separate them with
disentangled representation learning. Our proposed Adversarial Asymmetric
Training (AAT) algorithm can reliably disentangle robust and non-robust
representations without additional supervision on robustness. Empirical results
show our method does not only successfully preserve accuracy by combining two
representations, but also achieve much better disentanglement than previous
work.
中文翻译:
无需(额外)监督的无解码器鲁棒性解开
提出对抗性训练 (AT) 以通过仅从输入中提取稳健特征来减轻机器学习模型的对抗性脆弱性,然而,由于丢弃了非稳健但有用的特征,不可避免地导致精度严重降低。这促使我们保留健壮和非健壮的特征,并用解开的表示学习将它们分开。我们提出的对抗性非对称训练 (AAT) 算法可以可靠地分离鲁棒和非鲁棒表示,而无需对鲁棒性进行额外监督。实证结果表明,我们的方法不仅通过组合两种表示成功地保持了准确性,而且比以前的工作实现了更好的解开。
更新日期:2020-07-06
中文翻译:
无需(额外)监督的无解码器鲁棒性解开
提出对抗性训练 (AT) 以通过仅从输入中提取稳健特征来减轻机器学习模型的对抗性脆弱性,然而,由于丢弃了非稳健但有用的特征,不可避免地导致精度严重降低。这促使我们保留健壮和非健壮的特征,并用解开的表示学习将它们分开。我们提出的对抗性非对称训练 (AAT) 算法可以可靠地分离鲁棒和非鲁棒表示,而无需对鲁棒性进行额外监督。实证结果表明,我们的方法不仅通过组合两种表示成功地保持了准确性,而且比以前的工作实现了更好的解开。