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
Robust Reinforcement Learning on State Observations with Learned Optimal AdversaryInternational Conference on Learning Representations (ICLR), 2021 Huan Zhang Hongge Chen Duane S. Boning Cho-Jui Hsieh 242 193 0 21 Jan 2021
Fundamental Tradeoffs in Distributionally Adversarial TrainingInternational Conference on Machine Learning (ICML), 2021 M. Mehrabi Adel Javanmard Ryan A. Rossi Anup B. Rao Tung Mai AAML 154 19 0 15 Jan 2021
Scaling the Convex Barrier with Sparse Dual AlgorithmsJournal of machine learning research (JMLR), 2021 Alessandro De Palma Harkirat Singh Behl Rudy Bunel Juil Sock M. P. Kumar 262 10 0 14 Jan 2021
Adversarial Robustness by Design through Analog Computing and Synthetic GradientsIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 Alessandro Cappelli Ruben Ohana Julien Launay Laurent Meunier Iacopo Poli Florent Krzakala AAML 202 13 0 06 Jan 2021
Efficient Reachability Analysis of Closed-Loop Systems with Neural Network ControllersIEEE International Conference on Robotics and Automation (ICRA), 2021 Michael Everett Golnaz Habibi Jonathan P. How 141 20 0 05 Jan 2021
With False Friends Like These, Who Can Notice Mistakes?AAAI Conference on Artificial Intelligence (AAAI), 2020 Lue Tao Lei Feng Jinfeng Yi Songcan Chen AAML 301 6 0 29 Dec 2020
Improving the Certified Robustness of Neural Networks via Consistency Regularization Mengting Xu Tao Zhang Zhongnian Li Daoqiang Zhang AAML 114 0 0 24 Dec 2020
Bounding the Complexity of Formally Verifying Neural Networks: A Geometric ApproachIEEE Conference on Decision and Control (CDC), 2020 James Ferlez Yasser Shoukry 109 7 0 22 Dec 2020
Incentivizing Truthfulness Through Audits in Strategic ClassificationAAAI Conference on Artificial Intelligence (AAAI), 2020 Andrew Estornell Sanmay Das Yevgeniy Vorobeychik MLAU 73 10 0 16 Dec 2020
FoggySight: A Scheme for Facial Lookup PrivacyProceedings on Privacy Enhancing Technologies (PoPETs), 2020 Ivan Evtimov Pascal Sturmfels Tadayoshi Kohno PICV FedML 166 26 0 15 Dec 2020
Amata: An Annealing Mechanism for Adversarial Training AccelerationAAAI Conference on Artificial Intelligence (AAAI), 2019 Nanyang Ye Qianxiao Li Xiao-Yun Zhou Zhanxing Zhu AAML 213 16 0 15 Dec 2020
Adaptive Verifiable Training Using Pairwise Class SimilarityAAAI Conference on Artificial Intelligence (AAAI), 2020 Shiqi Wang Kevin Eykholt Taesung Lee Jiyong Jang Ian Molloy OOD 100 1 0 14 Dec 2020
Achieving Adversarial Robustness Requires An Active TeacherJournal of Computational Mathematics (JCM), 2020 Chao Ma Lexing Ying 134 1 0 14 Dec 2020
Attack Agnostic Detection of Adversarial Examples via Random Subspace AnalysisIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2020 Nathan G. Drenkow Neil Fendley Philippe Burlina AAML 275 7 0 11 Dec 2020
DSRNA: Differentiable Search of Robust Neural ArchitecturesComputer Vision and Pattern Recognition (CVPR), 2020 Ramtin Hosseini Xingyi Yang P. Xie OOD AAML 193 55 0 11 Dec 2020
Certifying Incremental Quadratic Constraints for Neural Networks via Convex OptimizationConference on Learning for Dynamics & Control (L4DC), 2020 Navid Hashemi Justin Ruths Mahyar Fazlyab 394 23 0 10 Dec 2020
Data-Dependent Randomized Smoothing Motasem Alfarra Adel Bibi Juil Sock Guohao Li UQCV 288 40 0 08 Dec 2020
A Singular Value Perspective on Model Robustness Malhar Jere Maghav Kumar F. Koushanfar AAML 182 7 0 07 Dec 2020
Interpretable Graph Capsule Networks for Object RecognitionAAAI Conference on Artificial Intelligence (AAAI), 2020 Jindong Gu Volker Tresp FAtt 208 41 0 03 Dec 2020
Generating private data with user customization Xiao Chen Thomas Navidi Ram Rajagopal 145 2 0 02 Dec 2020
Deterministic Certification to Adversarial Attacks via Bernstein Polynomial Approximation Ching-Chia Kao Jhe-Bang Ko Chun-Shien Lu AAML 162 1 0 28 Nov 2020
Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete VerifiersInternational Conference on Learning Representations (ICLR), 2020 Kaidi Xu Huan Zhang Shiqi Wang Yihan Wang Suman Jana Xue Lin Cho-Jui Hsieh 305 223 0 27 Nov 2020
A Study on the Uncertainty of Convolutional Layers in Deep Neural NetworksInternational Journal of Machine Learning and Cybernetics (IJMLC), 2020 Hao Shen Sihong Chen Ran Wang 136 7 0 27 Nov 2020
Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning Luiz F. O. Chamon Santiago Paternain Alejandro Ribeiro AAML 83 1 0 24 Nov 2020
A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations Can Bakiskan Metehan Cekic Ahmet Dundar Sezer Upamanyu Madhow AAML 111 0 0 21 Nov 2020
Adversarial Examples for $k$ -Nearest Neighbor Classifiers Based on Higher-Order Voronoi DiagramsNeural Information Processing Systems (NeurIPS), 2020 Chawin Sitawarin Evgenios M. Kornaropoulos Basel Alomair David Wagner AAML 179 10 0 19 Nov 2020
Extreme Value Preserving Networks Mingjie Sun Jianguo Li Changshui Zhang AAML MDE 117 0 0 17 Nov 2020
Adversarially Robust Classification based on GLRTIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 Bhagyashree Puranik Upamanyu Madhow Ramtin Pedarsani VLM AAML 157 4 0 16 Nov 2020
Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial PerturbationsInternational Conference on Learning Representations (ICLR), 2020 Jinyuan Jia Binghui Wang Xiaoyu Cao Hongbin Liu Neil Zhenqiang Gong 197 26 0 15 Nov 2020
Integer Programming-based Error-Correcting Output Code Design for Robust ClassificationConference on Uncertainty in Artificial Intelligence (UAI), 2020 Samarth Gupta Saurabh Amin 98 4 0 30 Oct 2020
Adversarial Robust Training of Deep Learning MRI Reconstruction ModelsMachine Learning for Biomedical Imaging (MLBI), 2020 Francesco Calivá Kaiyang Cheng Rutwik Shah V. Pedoia OOD AAML MedIm 256 13 0 30 Oct 2020
Reliable Graph Neural Networks via Robust AggregationNeural Information Processing Systems (NeurIPS), 2020 Simon Geisler Daniel Zügner Stephan Günnemann AAML OOD 146 85 0 29 Oct 2020
Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?International Conference on Machine Learning (ICML), 2020 Anna-Kathrin Kopetzki Bertrand Charpentier Daniel Zügner Sandhya Giri Stephan Günnemann 287 52 0 28 Oct 2020
$Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations$ Most ReLU Networks Suffer from $\ell^2$ Adversarial PerturbationsNeural Information Processing Systems (NeurIPS), 2020 Amit Daniely Hadas Shacham MLT 115 16 0 28 Oct 2020
An efficient nonconvex reformulation of stagewise convex optimization problemsNeural Information Processing Systems (NeurIPS), 2020 Rudy Bunel Oliver Hinder Srinadh Bhojanapalli Krishnamurthy Dvijotham Dvijotham OffRL 117 17 0 27 Oct 2020
ATRO: Adversarial Training with a Rejection Option Masahiro Kato Zhenghang Cui Yoshihiro Fukuhara AAML 163 11 0 24 Oct 2020
Adversarial Robustness of Supervised Sparse Coding Jeremias Sulam Ramchandran Muthumukar R. Arora AAML 230 25 0 22 Oct 2020
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming Sumanth Dathathri Krishnamurthy Dvijotham Alexey Kurakin Aditi Raghunathan J. Uesato ... Shreya Shankar Jacob Steinhardt Ian Goodfellow Abigail Z. Jacobs Pushmeet Kohli AAML 303 100 0 22 Oct 2020
Precise Statistical Analysis of Classification Accuracies for Adversarial Training Adel Javanmard Mahdi Soltanolkotabi AAML 357 66 0 21 Oct 2020
Certified Distributional Robustness on Smoothed Classifiers Jungang Yang Liyao Xiang Pengzhi Chu Yukun Wang Cheng Zhou Xinbing Wang AAML 152 1 0 21 Oct 2020
MINVO Basis: Finding Simplexes with Minimum Volume Enclosing Polynomial Curves J. Tordesillas Jonathan P. How 355 42 0 21 Oct 2020
Tight Second-Order Certificates for Randomized Smoothing Alexander Levine Aounon Kumar Thomas A. Goldstein Soheil Feizi AAML 107 16 0 20 Oct 2020
Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methodsEuropean Conference on Computer Vision (ECCV), 2020 Byungjoo Kim Bryce Chudomelka Jinyoung Park Jaewoo Kang Youngjoon Hong Hyunwoo J. Kim AAML 123 6 0 20 Oct 2020
RobustBench: a standardized adversarial robustness benchmark Francesco Croce Maksym Andriushchenko Vikash Sehwag Edoardo Debenedetti Nicolas Flammarion M. Chiang Prateek Mittal Matthias Hein VLM 691 809 0 19 Oct 2020
A Sequential Framework Towards an Exact SDP Verification of Neural NetworksInternational Conference on Data Science and Advanced Analytics (DSAA), 2020 Ziye Ma Somayeh Sojoudi 233 8 0 16 Oct 2020
Certifying Neural Network Robustness to Random Input Noise from Samples Brendon G. Anderson Somayeh Sojoudi AAML 134 9 0 15 Oct 2020
To be Robust or to be Fair: Towards Fairness in Adversarial Training Han Xu Xiaorui Liu Yaxin Li Anil K. Jain Shucheng Zhou 222 205 0 13 Oct 2020
Investigating the Robustness of Artificial Intelligent Algorithms with Mixture Experiments J. Lian Laura J. Freeman Yili Hong Xinwei Deng OOD 115 1 0 10 Oct 2020
Understanding Catastrophic Overfitting in Single-step Adversarial TrainingAAAI Conference on Artificial Intelligence (AAAI), 2020 Hoki Kim Woojin Lee Jaewook Lee AAML 344 123 0 05 Oct 2020
Geometry-aware Instance-reweighted Adversarial TrainingInternational Conference on Learning Representations (ICLR), 2020 Jingfeng Zhang Jianing Zhu Gang Niu Bo Han Masashi Sugiyama Mohan Kankanhalli AAML 289 302 0 05 Oct 2020