v1v2v3v4v5 (latest)

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Neural Information Processing Systems (NeurIPS), 2019

9 June 2019

ArXiv (abs)PDF HTML Github (225★)

Papers citing "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"

40 / 390 papers shown

Title
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond Kaidi Xu Zhouxing Shi Huan Zhang Yihan Wang Kai-Wei Chang Shiyu Huang B. Kailkhura Xinyu Lin Cho-Jui Hsieh AAML 267 15 0 28 Feb 2020
Certified Defense to Image Transformations via Randomized SmoothingNeural Information Processing Systems (NeurIPS), 2020 Marc Fischer Maximilian Baader Martin Vechev AAML 466 73 0 27 Feb 2020
TSS: Transformation-Specific Smoothing for Robustness CertificationConference on Computer and Communications Security (CCS), 2020 Linyi Li Maurice Weber Xiaojun Xu Luka Rimanic B. Kailkhura Tao Xie Ce Zhang Yue Liu AAML 416 61 0 27 Feb 2020
Overfitting in adversarially robust deep learningInternational Conference on Machine Learning (ICML), 2020 Leslie Rice Eric Wong Zico Kolter 517 883 0 26 Feb 2020
(De)Randomized Smoothing for Certifiable Defense against Patch AttacksNeural Information Processing Systems (NeurIPS), 2020 Alexander Levine Soheil Feizi AAML 218 173 0 25 Feb 2020
HYDRA: Pruning Adversarially Robust Neural Networks Vikash Sehwag Shiqi Wang Prateek Mittal Suman Jana AAML 196 25 0 24 Feb 2020
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based FrameworkNeural Information Processing Systems (NeurIPS), 2020 Dinghuai Zhang Mao Ye Chengyue Gong Zhanxing Zhu Qiang Liu AAML 208 68 0 21 Feb 2020
MaxUp: A Simple Way to Improve Generalization of Neural Network Training Chengyue Gong Zhaolin Ren Mao Ye Qiang Liu AAML 149 58 0 20 Feb 2020
Boosting Adversarial Training with Hypersphere EmbeddingNeural Information Processing Systems (NeurIPS), 2020 Tianyu Pang Xiao Yang Yinpeng Dong Kun Xu Jun Zhu Hang Su AAML 316 161 0 20 Feb 2020
Randomized Smoothing of All Shapes and SizesInternational Conference on Machine Learning (ICML), 2020 Greg Yang Tony Duan J. E. Hu Hadi Salman Ilya P. Razenshteyn Jungshian Li AAML 383 228 0 19 Feb 2020
Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable RobustnessAAAI Conference on Artificial Intelligence (AAAI), 2020 Huijie Feng Chunpeng Wu Guoyang Chen Weifeng Zhang Y. Ning AAML 115 12 0 17 Feb 2020
Adversarial Distributional Training for Robust Deep LearningNeural Information Processing Systems (NeurIPS), 2020 Yinpeng Dong Zhijie Deng Tianyu Pang Hang Su Jun Zhu OOD 169 137 0 14 Feb 2020
$Random Smoothing Might be Unable to Certify $\ell_\infty$ Robustness for High-Dimensional Images$ Random Smoothing Might be Unable to Certify $\ell_\infty$ Robustness for High-Dimensional ImagesJournal of machine learning research (JMLR), 2020 Avrim Blum Travis Dick N. Manoj Hongyang R. Zhang AAML 240 81 0 10 Feb 2020
Curse of Dimensionality on Randomized Smoothing for Certifiable RobustnessInternational Conference on Machine Learning (ICML), 2020 Aounon Kumar Alexander Levine Tom Goldstein Soheil Feizi 159 102 0 08 Feb 2020
Analysis of Random Perturbations for Robust Convolutional Neural Networks Adam Dziedzic S. Krishnan OOD AAML 278 1 0 08 Feb 2020
Certified Robustness to Label-Flipping Attacks via Randomized SmoothingInternational Conference on Machine Learning (ICML), 2020 Elan Rosenfeld Ezra Winston Pradeep Ravikumar J. Zico Kolter OOD AAML 434 171 0 07 Feb 2020
HRFA: High-Resolution Feature-based Attack Jia Cai Sizhe Chen Peidong Zhang Chengjin Sun Xiaolin Huang AAML 157 0 0 21 Jan 2020
Fast is better than free: Revisiting adversarial trainingInternational Conference on Learning Representations (ICLR), 2020 Eric Wong Leslie Rice J. Zico Kolter AAML OOD 709 1,287 0 12 Jan 2020
MACER: Attack-free and Scalable Robust Training via Maximizing Certified RadiusInternational Conference on Learning Representations (ICLR), 2020 Runtian Zhai Chen Dan Di He Huan Zhang Boqing Gong Pradeep Ravikumar Cho-Jui Hsieh Liwei Wang OOD AAML 494 188 0 08 Jan 2020
Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized SmoothingInternational Conference on Learning Representations (ICLR), 2019 Jinyuan Jia Xiaoyu Cao Binghui Wang Neil Zhenqiang Gong AAML 129 104 0 20 Dec 2019
$n$ -ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers Mahmood Sharif Lujo Bauer Michael K. Reiter AAML 100 8 0 19 Dec 2019
Constructing a provably adversarially-robust classifier from a high accuracy oneInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019 Grzegorz Gluch R. Urbanke AAML 74 2 0 16 Dec 2019
Training Provably Robust Models by Polyhedral Envelope RegularizationIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2019 Chen Liu Mathieu Salzmann Sabine Süsstrunk AAML 168 9 0 10 Dec 2019
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like OneInternational Conference on Learning Representations (ICLR), 2019 Will Grathwohl Kuan-Chieh Wang J. Jacobsen David Duvenaud Mohammad Norouzi Kevin Swersky VLM 417 593 0 06 Dec 2019
Robustness Certificates for Sparse Adversarial Attacks by Randomized AblationAAAI Conference on Artificial Intelligence (AAAI), 2019 Alexander Levine Soheil Feizi AAML 201 111 0 21 Nov 2019
Smoothed Inference for Adversarially-Trained Models Yaniv Nemcovsky Evgenii Zheltonozhskii Chaim Baskin Brian Chmiel Maxim Fishman A. Bronstein A. Mendelson AAML FedML 143 2 0 17 Nov 2019
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional NetworksNeural Information Processing Systems (NeurIPS), 2019 Qiyang Li Saminul Haque Cem Anil James Lucas Roger C. Grosse Joern-Henrik Jacobsen 321 119 0 03 Nov 2019
Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial AttacksInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019 Alexander Levine Soheil Feizi AAML 117 63 0 23 Oct 2019
Are Perceptually-Aligned Gradients a General Property of Robust Classifiers? Simran Kaur Jeremy M. Cohen Zachary Chase Lipton OOD AAML 216 68 0 18 Oct 2019
Extracting robust and accurate features via a robust information bottleneckIEEE Journal on Selected Areas in Information Theory (JSAIT), 2019 Ankit Pensia Varun Jog Po-Ling Loh AAML 134 23 0 15 Oct 2019
Towards Robust Direct Perception Networks for Automated Driving Chih-Hong Cheng 76 1 0 30 Sep 2019
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts Yu Sun Xiaolong Wang Zhuang Liu John Miller Alexei A. Efros Moritz Hardt TTA OOD 271 104 0 29 Sep 2019
Additive function approximation in the brain K. Harris 147 14 0 05 Sep 2019
Towards Stable and Efficient Training of Verifiably Robust Neural NetworksInternational Conference on Learning Representations (ICLR), 2019 Huan Zhang Hongge Chen Chaowei Xiao Sven Gowal Robert Stanforth Yue Liu Duane S. Boning Cho-Jui Hsieh AAML 316 371 0 14 Jun 2019
Provably Robust Boosted Decision Stumps and Trees against Adversarial AttacksNeural Information Processing Systems (NeurIPS), 2019 Maksym Andriushchenko Matthias Hein 187 66 0 08 Jun 2019
Certifiably Robust Interpretation in Deep Learning Alexander Levine Sahil Singla Soheil Feizi FAtt AAML 303 65 0 28 May 2019
Scaleable input gradient regularization for adversarial robustnessMachine Learning with Applications (MLWA), 2019 Chris Finlay Adam M. Oberman AAML 237 84 0 27 May 2019
Robust Neural Networks using Randomized Adversarial Training Alexandre Araujo Laurent Meunier Rafael Pinot Benjamin Négrevergne AAML OOD 232 36 0 25 Mar 2019
A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks Hadi Salman Greg Yang Huan Zhang Cho-Jui Hsieh Pengchuan Zhang AAML 447 280 0 23 Feb 2019
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen Elan Rosenfeld J. Zico Kolter AAML 831 2,265 0 08 Feb 2019