Less is More: Culling the Training Set to Improve Robustness of Deep
Neural Networks

v1v2 (latest)

Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks

9 January 2018

ArXiv (abs)PDF HTML

Papers citing "Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks"

11 / 11 papers shown

Title
MagNet: a Two-Pronged Defense against Adversarial Examples Dongyu Meng Hao Chen AAML 56 1,209 0 25 May 2017
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods Nicholas Carlini D. Wagner AAML 131 1,867 0 20 May 2017
Understanding Black-box Predictions via Influence Functions Pang Wei Koh Percy Liang TDI 229 2,910 0 14 Mar 2017
On Detecting Adversarial Perturbations J. H. Metzen Tim Genewein Volker Fischer Bastian Bischoff AAML 85 950 0 14 Feb 2017
"Influence Sketching": Finding Influential Samples In Large-Scale Regressions M. Wojnowicz Ben Cruz Xuan Zhao Brian Wallace Matt Wolff Jay Luan Caleb Crable TDI 84 32 0 17 Nov 2016
Towards Evaluating the Robustness of Neural Networks Nicholas Carlini D. Wagner OOD AAML 284 8,593 0 16 Aug 2016
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 551 5,914 0 08 Jul 2016
DeepFool: a simple and accurate method to fool deep neural networks Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi P. Frossard AAML 160 4,910 0 14 Nov 2015
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks Nicolas Papernot Patrick McDaniel Xi Wu S. Jha A. Swami AAML 120 3,078 0 14 Nov 2015
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 284 19,145 0 20 Dec 2014
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 297 14,978 1 21 Dec 2013

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.