v1v2v3 (latest)

Provable defenses against adversarial examples via the convex outer adversarial polytope

2 November 2017

Eric Wong

J. Zico Kolter

AAML

ArXiv (abs)PDF HTML Github (387★)

Papers citing "Provable defenses against adversarial examples via the convex outer adversarial polytope"

50 / 957 papers shown

Title
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations Eric Wong Frank R. Schmidt J. Zico Kolter AAML 226 222 0 21 Feb 2019
advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch G. Ding Luyu Wang Xiaomeng Jin 169 195 0 20 Feb 2019
Fast Neural Network Verification via Shadow Prices Vicencc Rubies-Royo Roberto Calandra D. Stipanović Claire Tomlin AAML 193 43 0 19 Feb 2019
On Evaluating Adversarial Robustness Nicholas Carlini Anish Athalye Nicolas Papernot Wieland Brendel Jonas Rauber Dimitris Tsipras Ian Goodfellow Aleksander Madry Alexey Kurakin ELM AAML 425 954 0 18 Feb 2019
VC Classes are Adversarially Robustly Learnable, but Only ImproperlyAnnual Conference Computational Learning Theory (COLT), 2019 Omar Montasser Steve Hanneke Nathan Srebro 234 145 0 12 Feb 2019
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen Elan Rosenfeld J. Zico Kolter AAML 811 2,265 0 08 Feb 2019
Robustness Certificates Against Adversarial Examples for ReLU Networks Sahil Singla Soheil Feizi AAML 134 21 0 01 Feb 2019
A New Family of Neural Networks Provably Resistant to Adversarial Attacks Rakshit Agrawal Luca de Alfaro D. Helmbold AAML OOD 58 2 0 01 Feb 2019
Augmenting Model Robustness with Transformation-Invariant Attacks Houpu Yao Zhe Wang Guangyu Nie Yassine Mazboudi Yezhou Yang Yi Ren AAML OOD 130 3 0 31 Jan 2019
A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance A. Shamir Itay Safran Eyal Ronen O. Dunkelman GAN AAML 126 96 0 30 Jan 2019
Defense Methods Against Adversarial Examples for Recurrent Neural Networks Ishai Rosenberg A. Shabtai Yuval Elovici Lior Rokach AAML GAN 192 44 0 28 Jan 2019
Characterizing the Shape of Activation Space in Deep Neural Networks Thomas Gebhart Paul Schrater Alan Hylton AAML 131 7 0 28 Jan 2019
On the (In)fidelity and Sensitivity for Explanations Chih-Kuan Yeh Cheng-Yu Hsieh A. Suggala David I. Inouye Pradeep Ravikumar FAtt 287 520 0 27 Jan 2019
Theoretically Principled Trade-off between Robustness and Accuracy Hongyang R. Zhang Yaodong Yu Jiantao Jiao Eric Xing L. Ghaoui Sai Li 690 2,832 0 24 Jan 2019
The Limitations of Adversarial Training and the Blind-Spot Attack Huan Zhang Hongge Chen Zhao Song Duane S. Boning Inderjit S. Dhillon Cho-Jui Hsieh AAML 169 153 0 15 Jan 2019
PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach Tsui-Wei Weng Pin-Yu Chen Lam M. Nguyen M. Squillante Ivan Oseledets Luca Daniel AAML 198 30 0 18 Dec 2018
A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability Xiaowei Huang Daniel Kroening Wenjie Ruan Marta Kwiatkowska Youcheng Sun Emese Thamo Min Wu Xinping Yi AAML 428 52 0 18 Dec 2018
Designing Adversarially Resilient Classifiers using Resilient Feature Engineering Kevin Eykholt A. Prakash AAML 108 4 0 17 Dec 2018
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem Matthias Hein Maksym Andriushchenko Julian Bitterwolf OODD 352 597 0 13 Dec 2018
On the Security of Randomized Defenses Against Adversarial Samples K. Sharad G. Marson H. Truong Ghassan O. Karame AAML 106 1 0 11 Dec 2018
Adversarial Attacks, Regression, and Numerical Stability Regularization A. Nguyen Edward Raff AAML 121 32 0 07 Dec 2018
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks Akhilan Boopathy Tsui-Wei Weng Pin-Yu Chen Sijia Liu Luca Daniel AAML 263 145 0 29 Nov 2018
A randomized gradient-free attack on ReLU networks Francesco Croce Matthias Hein AAML 123 23 0 28 Nov 2018
Strong mixed-integer programming formulations for trained neural networksMathematical programming (Math. Program.), 2018 Ross Anderson Joey Huchette Christian Tjandraatmadja J. Vielma 366 283 0 20 Nov 2018
Lightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples Hajime Ono Tsubasa Takahashi Kazuya Kakizaki AAML 70 4 0 20 Nov 2018
A Statistical Approach to Assessing Neural Network RobustnessInternational Conference on Learning Representations (ICLR), 2018 Stefan Webb Tom Rainforth Yee Whye Teh M. P. Kumar AAML 259 92 0 17 Nov 2018
nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems Chih-Hong Cheng Chung-Hao Huang Georg Nührenberg 146 11 0 16 Nov 2018
A Spectral View of Adversarially Robust FeaturesNeural Information Processing Systems (NeurIPS), 2018 Shivam Garg Willie Neiswanger B. Zhang Gregory Valiant AAML 220 22 0 15 Nov 2018
Theoretical Analysis of Adversarial Learning: A Minimax Approach Zhuozhuo Tu Jingwei Zhang Dacheng Tao AAML 126 71 0 13 Nov 2018
AdVersarial: Perceptual Ad Blocking meets Adversarial Machine LearningConference on Computer and Communications Security (CCS), 2018 K. Makarychev Pascal Dupré Yury Makarychev Giancarlo Pellegrino Dan Boneh AAML 231 65 0 08 Nov 2018
MixTrain: Scalable Training of Verifiably Robust Neural Networks Yue Zhang Yizheng Chen Ahmed Abdou Mohsen Guizani AAML 90 25 0 06 Nov 2018
Semidefinite relaxations for certifying robustness to adversarial examples Aditi Raghunathan Jacob Steinhardt Abigail Z. Jacobs AAML 299 449 0 02 Nov 2018
Efficient Neural Network Robustness Certification with General Activation Functions Huan Zhang Tsui-Wei Weng Pin-Yu Chen Cho-Jui Hsieh Luca Daniel AAML 320 831 0 02 Nov 2018
Stronger Data Poisoning Attacks Break Data Sanitization Defenses Pang Wei Koh Jacob Steinhardt Abigail Z. Jacobs 265 267 0 02 Nov 2018
On the Geometry of Adversarial Examples Marc Khoury Dylan Hadfield-Menell AAML 240 83 0 01 Nov 2018
On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models Sven Gowal Krishnamurthy Dvijotham Robert Stanforth Rudy Bunel Chongli Qin J. Uesato Relja Arandjelović Timothy A. Mann Pushmeet Kohli AAML 371 599 0 30 Oct 2018
Logit Pairing Methods Can Fool Gradient-Based Attacks Marius Mosbach Maksym Andriushchenko T. A. Trost Matthias Hein Dietrich Klakow AAML 110 85 0 29 Oct 2018
Rademacher Complexity for Adversarially Robust Generalization Dong Yin Kannan Ramchandran Peter L. Bartlett AAML 347 278 0 29 Oct 2018
RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications Huan Zhang Pengchuan Zhang Cho-Jui Hsieh AAML 132 66 0 28 Oct 2018
Towards Robust Deep Neural Networks Timothy E. Wang Jack Gu D. Mehta Xiaojun Zhao Edgar A. Bernal OOD 215 11 0 27 Oct 2018
Robust Adversarial Learning via Sparsifying Front Ends S. Gopalakrishnan Zhinus Marzi Metehan Cekic Upamanyu Madhow Ramtin Pedarsani AAML 138 3 0 24 Oct 2018
Adversarial Risk Bounds via Function Transformation Justin Khim Po-Ling Loh AAML 132 50 0 22 Oct 2018
Cost-Sensitive Robustness against Adversarial Examples Xiao Zhang David Evans AAML 172 26 0 22 Oct 2018
Provable Robustness of ReLU networks via Maximization of Linear Regions Francesco Croce Maksym Andriushchenko Matthias Hein 215 169 0 17 Oct 2018
Combinatorial Attacks on Binarized Neural Networks Elias Boutros Khalil Amrita Gupta B. Dilkina AAML 166 42 0 08 Oct 2018
Empirical Bounds on Linear Regions of Deep Rectifier Networks Thiago Serra Srikumar Ramalingam 288 43 0 08 Oct 2018
Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness Chihuang Liu Joseph Jaja AAML 169 13 0 04 Oct 2018
Verification for Machine Learning, Autonomy, and Neural Networks Survey Weiming Xiang Patrick Musau A. Wild Diego Manzanas Lopez Nathaniel P. Hamilton Xiaodong Yang Joel A. Rosenfeld Taylor T. Johnson 160 105 0 03 Oct 2018
Adversarial Examples - A Complete Characterisation of the Phenomenon A. Serban E. Poll Joost Visser SILM AAML 196 49 0 02 Oct 2018
Improving the Generalization of Adversarial Training with Domain Adaptation Chuanbiao Song Kun He Liwei Wang John E. Hopcroft AAML OOD 252 144 0 01 Oct 2018