随笔分类 -  Robust Learning

上一页 1 2 3 4 5
Understanding Black-box Predictions via Influence Functions
摘要：Koh P W, Liang P. Understanding black-box predictions via influence functions[C]. international conference on machine learning, 2017: 1885-1894. @arti 阅读全文
posted @ 2020-05-21 21:06 馒头and花卷 阅读(422) 评论(0) 推荐(0) 编辑
Adversarial Examples Are Not Bugs, They Are Features
摘要：Ilyas A, Santurkar S, Tsipras D, et al. Adversarial Examples Are Not Bugs, They Are Features[C]. neural information processing systems, 2019: 125-136. 阅读全文
posted @ 2020-05-15 16:07 馒头and花卷 阅读(693) 评论(17) 推荐(1) 编辑
DeepFool: a simple and accurate method to fool deep neural networks
摘要：Moosavidezfooli S, Fawzi A, Frossard P, et al. DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks[C]. computer vision and pattern rec 阅读全文
posted @ 2020-05-07 21:27 馒头and花卷 阅读(609) 评论(2) 推荐(0) 编辑
The Limitations of Deep Learning in Adversarial Settings
摘要：Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z. Berkay Celik, Ananthram Swami, The Limitations of Deep Learning in Adversarial Set 阅读全文
posted @ 2020-05-07 11:34 馒头and花卷 阅读(485) 评论(6) 推荐(1) 编辑
ADVERSARIAL EXAMPLES IN THE PHYSICAL WORLD
摘要：Alexey Kurakin, Ian J. Goodfellow, Samy Bengio, ADVERSARIAL EXAMPLES IN THE PHYSICAL WORLD 概 有很多种方法能够生成对抗样本(adversarial samples), 但是真实世界中是否存在这样的对抗样本呢? 阅读全文
posted @ 2020-05-05 20:31 馒头and花卷 阅读(1108) 评论(4) 推荐(0) 编辑
One Pixel Attack for Fooling Deep Neural Networks
摘要：Su J, Vargas D V, Sakurai K, et al. One Pixel Attack for Fooling Deep Neural Networks[J]. IEEE Transactions on Evolutionary Computation, 2019, 23(5): 阅读全文
posted @ 2020-04-14 14:41 馒头and花卷 阅读(337) 评论(0) 推荐(0) 编辑
Towards Evaluating the Robustness of Neural Networks
摘要：Nicholas Carlini, David Wagner, Towards Evaluating the Robustness of Neural Networks 概 提出了在不同范数下ℓ0,ℓ2,ℓ∞下生成adversarial samples的 阅读全文
posted @ 2020-04-08 16:54 馒头and花卷 阅读(756) 评论(0) 推荐(0) 编辑
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
摘要：Nicolas Papernot, Patrick McDaniel, Xi Wu, Somesh Jha, Ananthram Swami, Distillation as a Defense to Adversarial Perturbations against Deep Neural Net 阅读全文
posted @ 2020-04-08 16:50 馒头and花卷 阅读(408) 评论(1) 推荐(0) 编辑
AUGMIX : A SIMPLE DATA PROCESSING METHOD TO IMPROVE ROBUSTNESS AND UNCERTAINTY
摘要：Dan Hendrycks, Norman Mu,, et. al, AUGMIX : A SIMPLE DATA PROCESSING METHOD TO IMPROVE ROBUSTNESS AND UNCERTAINTY. 概 本文介绍AUGMIX算法——对现有的的一些augmentation 阅读全文
posted @ 2020-03-24 13:49 馒头and花卷 阅读(595) 评论(0) 推荐(0) 编辑
Adversarial Examples Improve Image Recognition
摘要：Xie C, Tan M, Gong B, et al. Adversarial Examples Improve Image Recognition.[J]. arXiv: Computer Vision and Pattern Recognition, 2019. @article{xie201 阅读全文
posted @ 2020-03-12 14:59 馒头and花卷 阅读(1311) 评论(0) 推荐(0) 编辑
Theoretically Principled Trade-off between Robustness and Accuracy
摘要：Zhang H, Yu Y, Jiao J, et al. Theoretically Principled Trade-off between Robustness and Accuracy[J]. arXiv: Learning, 2019. @article{zhang2019theoreti 阅读全文
posted @ 2020-03-12 14:24 馒头and花卷 阅读(1454) 评论(0) 推荐(0) 编辑
Towards Deep Learning Models Resistant to Adversarial Attacks
摘要：Madry A, Makelov A, Schmidt L, et al. Towards Deep Learning Models Resistant to Adversarial Attacks.[J]. arXiv: Machine Learning, 2017. @article{madry 阅读全文
posted @ 2020-03-04 20:08 馒头and花卷 阅读(904) 评论(0) 推荐(0) 编辑
EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES
摘要：Goodfellow I, Shlens J, Szegedy C, et al. Explaining and Harnessing Adversarial Examples[J]. arXiv: Machine Learning, 2014. @article{goodfellow2014exp 阅读全文
posted @ 2020-03-04 19:35 馒头and花卷 阅读(463) 评论(0) 推荐(0) 编辑
Practical Black-Box Attacks against Machine Learning
摘要：Papernot N, Mcdaniel P, Goodfellow I, et al. Practical Black-Box Attacks against Machine Learning[C]. computer and communications security, 2017: 506- 阅读全文
posted @ 2020-03-04 19:32 馒头and花卷 阅读(375) 评论(0) 推荐(1) 编辑

上一页 1 2 3 4 5
点击右上角即可分享
微信分享提示