Improving the Adversarial Robustness and Interpretability of Deep Neural
Networks by Regularizing their Input Gradients

Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients

26 November 2017

Finale Doshi-Velez

Papers citing "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

9 / 109 papers shown

Title
Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks Ambra Demontis Marco Melis Maura Pintor Matthew Jagielski Battista Biggio Alina Oprea Cristina Nita-Rotaru Fabio Roli SILM AAML 11 11 0 08 Sep 2018
Security Consideration For Deep Learning-Based Image Forensics Wei-Ye Zhao Pengpeng Yang R. Ni Yao-Min Zhao Haorui Wu AAML 6 5 0 29 Mar 2018
Understanding and Enhancing the Transferability of Adversarial Examples Lei Wu Zhanxing Zhu Cheng Tai E. Weinan AAML SILM 28 96 0 27 Feb 2018
Deep Defense: Training DNNs with Improved Adversarial Robustness Ziang Yan Yiwen Guo Changshui Zhang AAML 33 109 0 23 Feb 2018
L2-Nonexpansive Neural Networks Haifeng Qian M. Wegman 17 74 0 22 Feb 2018
Gradient Regularization Improves Accuracy of Discriminative Models D. Varga Adrián Csiszárik Zsolt Zombori 18 53 0 28 Dec 2017
Interpretation of Neural Networks is Fragile Amirata Ghorbani Abubakar Abid James Zou FAtt AAML 48 856 0 29 Oct 2017
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 264 3,110 0 04 Nov 2016
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 287 5,837 0 08 Jul 2016