Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck

6 April 2022

Papers citing "Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck"

26 / 26 papers shown

Title
Robust Feature Learning for Multi-Index Models in High Dimensions Alireza Mousavi-Hosseini Adel Javanmard Murat A. Erdogdu OOD AAML 126 1 0 21 Oct 2024
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data Binghui Li Yuanzhi Li OOD 68 3 0 11 Oct 2024
Transferable Perturbations of Deep Feature Distributions Nathan Inkawhich Kevin J. Liang Lawrence Carin Yiran Chen AAML 61 87 0 27 Apr 2020
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks Francesco Croce Matthias Hein AAML 227 1,858 0 03 Mar 2020
Restricting the Flow: Information Bottlenecks for Attribution Karl Schulz Leon Sixt Federico Tombari Tim Landgraf FAtt 61 190 0 02 Jan 2020
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack Francesco Croce Matthias Hein AAML 101 490 0 03 Jul 2019
IoT Network Security from the Perspective of Adversarial Deep Learning Y. Sagduyu Yi Shi T. Erpek AAML 46 78 0 31 May 2019
Adversarial Examples Are Not Bugs, They Are Features Andrew Ilyas Shibani Santurkar Dimitris Tsipras Logan Engstrom Brandon Tran Aleksander Madry SILM 93 1,844 0 06 May 2019
Understanding Neural Networks via Feature Visualization: A survey Anh Nguyen J. Yosinski Jeff Clune FAtt 76 161 0 18 Apr 2019
On instabilities of deep learning in image reconstruction - Does AI come at a cost? Vegard Antun F. Renna C. Poon Ben Adcock A. Hansen 59 605 0 14 Feb 2019
Excessive Invariance Causes Adversarial Vulnerability J. Jacobsen Jens Behrmann R. Zemel Matthias Bethge AAML 71 166 0 01 Nov 2018
Are adversarial examples inevitable? Ali Shafahi Wenjie Huang Christoph Studer Soheil Feizi Tom Goldstein SILM 74 283 0 06 Sep 2018
Robustness May Be at Odds with Accuracy Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner Aleksander Madry AAML 108 1,782 0 30 May 2018
Adversarially Robust Generalization Requires More Data Ludwig Schmidt Shibani Santurkar Dimitris Tsipras Kunal Talwar Aleksander Madry OOD AAML 157 795 0 30 Apr 2018
Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks Ruth C. Fong Andrea Vedaldi FAtt 77 264 0 10 Jan 2018
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models Pin-Yu Chen Huan Zhang Yash Sharma Jinfeng Yi Cho-Jui Hsieh AAML 85 1,885 0 14 Aug 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 317 12,131 0 19 Jun 2017
Network Dissection: Quantifying Interpretability of Deep Visual Representations David Bau Bolei Zhou A. Khosla A. Oliva Antonio Torralba MILM FAtt 158 1,523 1 19 Apr 2017
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 472 3,148 0 04 Nov 2016
Towards Evaluating the Robustness of Neural Networks Nicholas Carlini D. Wagner OOD AAML 282 8,583 0 16 Aug 2016
Wide Residual Networks Sergey Zagoruyko N. Komodakis 353 8,000 0 23 May 2016
Practical Black-Box Attacks against Machine Learning Nicolas Papernot Patrick McDaniel Ian Goodfellow S. Jha Z. Berkay Celik A. Swami MLAU AAML 75 3,682 0 08 Feb 2016
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 282 19,121 0 20 Dec 2014
Understanding Deep Image Representations by Inverting Them Aravindh Mahendran Andrea Vedaldi FAtt 131 1,965 0 26 Nov 2014
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 282 14,963 1 21 Dec 2013
Visualizing and Understanding Convolutional Networks Matthew D. Zeiler Rob Fergus FAtt SSL 595 15,904 0 12 Nov 2013