MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples

22 November 2017

Papers citing "MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples"

9 / 9 papers shown

Title
Adversarial Examples on Object Recognition: A Comprehensive Survey A. Serban E. Poll Joost Visser AAML 65 73 0 07 Aug 2020
Efficient Defenses Against Adversarial Attacks Valentina Zantedeschi Maria-Irina Nicolae Ambrish Rawat AAML 33 297 0 21 Jul 2017
APE-GAN: Adversarial Perturbation Elimination with GAN Shiwei Shen Guoqing Jin Feng Dai Yongdong Zhang GAN 49 216 0 18 Jul 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 227 11,962 0 19 Jun 2017
MagNet: a Two-Pronged Defense against Adversarial Examples Dongyu Meng Hao Chen AAML 33 1,205 0 25 May 2017
Delving into Transferable Adversarial Examples and Black-box Attacks Yanpei Liu Xinyun Chen Chang-rui Liu D. Song AAML 120 1,727 0 08 Nov 2016
Towards Evaluating the Robustness of Neural Networks Nicholas Carlini D. Wagner OOD AAML 168 8,513 0 16 Aug 2016
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 163 18,922 0 20 Dec 2014
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 166 14,831 1 21 Dec 2013