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
CAQL: Continuous Action Q-LearningInternational Conference on Learning Representations (ICLR), 2019 Moonkyung Ryu Yinlam Chow Ross Anderson Christian Tjandraatmadja Craig Boutilier 489 47 0 26 Sep 2019
Lower Bounds on Adversarial Robustness from Optimal TransportNeural Information Processing Systems (NeurIPS), 2019 A. Bhagoji Daniel Cullina Prateek Mittal OOD OT AAML 168 97 0 26 Sep 2019
Towards neural networks that provably know when they don't knowInternational Conference on Learning Representations (ICLR), 2019 Alexander Meinke Matthias Hein OODD 232 147 0 26 Sep 2019
Defending Against Physically Realizable Attacks on Image ClassificationInternational Conference on Learning Representations (ICLR), 2019 Tong Wu Liang Tong Yevgeniy Vorobeychik AAML 238 141 0 20 Sep 2019
Adversarial Vulnerability Bounds for Gaussian Process ClassificationMachine-mediated learning (ML), 2019 M. Smith Kathrin Grosse Michael Backes Mauricio A. Alvarez AAML 103 9 0 19 Sep 2019
Adversarial Attacks and Defenses in Images, Graphs and Text: A ReviewInternational Journal of Automation and Computing (IJAC), 2019 Han Xu Yao Ma Haochen Liu Debayan Deb Hui Liu Shucheng Zhou Anil K. Jain AAML 291 725 0 17 Sep 2019
Neural Belief ReasonerInternational Joint Conference on Artificial Intelligence (IJCAI), 2019 Haifeng Qian NAI BDL 124 1 0 10 Sep 2019
Adversarial Robustness Against the Union of Multiple Perturbation ModelsInternational Conference on Machine Learning (ICML), 2019 Pratyush Maini Eric Wong J. Zico Kolter OOD AAML 233 163 0 09 Sep 2019
Achieving Verified Robustness to Symbol Substitutions via Interval Bound PropagationConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 Po-Sen Huang Robert Stanforth Johannes Welbl Chris Dyer Dani Yogatama Sven Gowal Krishnamurthy Dvijotham Pushmeet Kohli AAML 208 173 0 03 Sep 2019
Certified Robustness to Adversarial Word SubstitutionsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 Robin Jia Aditi Raghunathan Kerem Göksel Abigail Z. Jacobs AAML 476 320 0 03 Sep 2019
Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective Guan-Horng Liu Evangelos A. Theodorou AI4CE 266 74 0 28 Aug 2019
Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation Yuh-Shyang Wang Tsui-Wei Weng Luca Daniel AAML 109 17 0 18 Aug 2019
Implicit Deep LearningSIAM Journal on Mathematics of Data Science (SIMODS), 2019 L. Ghaoui Fangda Gu Bertrand Travacca Armin Askari Alicia Y. Tsai AI4CE 331 198 0 17 Aug 2019
Adversarial shape perturbations on 3D point clouds Daniel Liu Ronald Yu Hao Su 3DPC 204 12 0 16 Aug 2019
A Survey of Recent Scalability Improvements for Semidefinite Programming with Applications in Machine Learning, Control, and Robotics Anirudha Majumdar G. Hall Amir Ali Ahmadi 226 110 0 14 Aug 2019
Adversarial Neural Pruning with Latent Vulnerability Suppression Divyam Madaan Jinwoo Shin Sung Ju Hwang AAML 203 3 0 12 Aug 2019
Refactoring Neural Networks for Verification David Shriver Dong Xu Sebastian G. Elbaum Matthew B. Dwyer 110 8 0 06 Aug 2019
Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin Kaiwen Wu Yaoliang Yu AAML 108 9 0 26 Jul 2019
Connecting Lyapunov Control Theory to Adversarial Attacks Arash Rahnama A. Nguyen Edward Raff AAML 101 6 0 17 Jul 2019
ART: Abstraction Refinement-Guided Training for Provably Correct Neural NetworksFormal Methods in Computer-Aided Design (FMCAD), 2019 Xuankang Lin He Zhu R. Samanta Suresh Jagannathan AAML 190 29 0 17 Jul 2019
Recovery Guarantees for Compressible Signals with Adversarial Noise J. Dhaliwal Kyle Hambrook AAML 156 2 0 15 Jul 2019
Towards Robust, Locally Linear Deep NetworksInternational Conference on Learning Representations (ICLR), 2019 Guang-He Lee David Alvarez-Melis Tommi Jaakkola ODL 186 48 0 07 Jul 2019
Accurate, reliable and fast robustness evaluationNeural Information Processing Systems (NeurIPS), 2019 Wieland Brendel Jonas Rauber Matthias Kümmerer Ivan Ustyuzhaninov Matthias Bethge AAML OOD 281 116 0 01 Jul 2019
Certifiable Robustness and Robust Training for Graph Convolutional NetworksKnowledge Discovery and Data Mining (KDD), 2019 Daniel Zügner Stephan Günnemann OffRL 140 174 0 28 Jun 2019
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustnessNeural Information Processing Systems (NeurIPS), 2019 Fanny Yang Zuowen Wang C. Heinze-Deml 261 46 0 26 Jun 2019
Quantitative Verification of Neural Networks And its Security ApplicationsConference on Computer and Communications Security (CCS), 2019 Teodora Baluta Shiqi Shen Shweta Shinde Kuldeep S. Meel P. Saxena AAML 196 113 0 25 Jun 2019
Convergence of Adversarial Training in Overparametrized Neural NetworksNeural Information Processing Systems (NeurIPS), 2019 Ruiqi Gao Tianle Cai Haochuan Li Liwei Wang Cho-Jui Hsieh Jason D. Lee AAML 260 113 0 19 Jun 2019
The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks F. Assion Peter Schlicht Florens Greßner W. Günther Fabian Hüger Nico M. Schmidt Umair Rasheed AAML 132 16 0 17 Jun 2019
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy Alex Lamb Vikas Verma Kenji Kawaguchi Alexander Matyasko Savya Khosla Arno Solin Yoshua Bengio AAML 401 106 0 16 Jun 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
Towards Compact and Robust Deep Neural Networks Vikash Sehwag Shiqi Wang Prateek Mittal Suman Jana AAML 129 41 0 14 Jun 2019
Tight Certificates of Adversarial Robustness for Randomly Smoothed ClassifiersNeural Information Processing Systems (NeurIPS), 2019 Guang-He Lee Yang Yuan Shiyu Chang Tommi Jaakkola AAML 200 134 0 12 Jun 2019
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural NetworksNeural Information Processing Systems (NeurIPS), 2019 Mahyar Fazlyab Avi Schwarzschild Hamed Hassani M. Morari George J. Pappas 363 511 0 12 Jun 2019
Evaluating the Robustness of Nearest Neighbor Classifiers: A Primal-Dual Perspective Lu Wang Xuanqing Liu Jinfeng Yi Zhi Zhou Cho-Jui Hsieh AAML 149 22 0 10 Jun 2019
Robustness Verification of Tree-based ModelsNeural Information Processing Systems (NeurIPS), 2019 Hongge Chen Huan Zhang Si Si Yang Li Duane S. Boning Cho-Jui Hsieh AAML 215 87 0 10 Jun 2019
Provably Robust Deep Learning via Adversarially Trained Smoothed ClassifiersNeural Information Processing Systems (NeurIPS), 2019 Hadi Salman Greg Yang Jungshian Li Pengchuan Zhang Huan Zhang Ilya P. Razenshteyn Sébastien Bubeck AAML 577 588 0 09 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
ML-LOO: Detecting Adversarial Examples with Feature AttributionAAAI Conference on Artificial Intelligence (AAAI), 2019 Puyudi Yang Jianbo Chen Cho-Jui Hsieh Jane-ling Wang Sai Li AAML 157 110 0 08 Jun 2019
Enhancing Gradient-based Attacks with Symbolic Intervals Shiqi Wang Yizheng Chen Ahmed Abdou Suman Jana AAML 104 15 0 05 Jun 2019
Adversarial Training is a Form of Data-dependent Operator Norm Regularization Kevin Roth Yannic Kilcher Thomas Hofmann 186 13 0 04 Jun 2019
Architecture Selection via the Trade-off Between Accuracy and Robustness Zhun Deng Cynthia Dwork Jialiang Wang Yao-Min Zhao AAML 228 5 0 04 Jun 2019
Correctness Verification of Neural Networks Yichen Yang Martin Rinard AAML 135 13 0 03 Jun 2019
Fast and Stable Interval Bounds Propagation for Training Verifiably Robust ModelsThe European Symposium on Artificial Neural Networks (ESANN), 2019 P. Morawiecki Przemysław Spurek Marek Śmieja Jacek Tabor AAML OOD 107 9 0 03 Jun 2019
Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable RobustnessInternational Joint Conference on Artificial Intelligence (IJCAI), 2019 Nhathai Phan Minh Nhat Vu Yang Liu R. Jin Dejing Dou Xintao Wu My T. Thai AAML 129 56 0 02 Jun 2019
Unlabeled Data Improves Adversarial RobustnessNeural Information Processing Systems (NeurIPS), 2019 Y. Carmon Aditi Raghunathan Ludwig Schmidt Abigail Z. Jacobs John C. Duchi 482 788 0 31 May 2019
Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way ForwardIEEE Communications Surveys and Tutorials (COMST), 2019 A. Qayyum Muhammad Usama Junaid Qadir Ala I. Al-Fuqaha AAML 164 209 0 29 May 2019
Empirically Measuring Concentration: Fundamental Limits on Intrinsic RobustnessNeural Information Processing Systems (NeurIPS), 2019 Saeed Mahloujifar Xiao Zhang Mohammad Mahmoody David Evans 217 23 0 29 May 2019
Controlling Neural Level SetsNeural Information Processing Systems (NeurIPS), 2019 Matan Atzmon Niv Haim Lior Yariv Ofer Israelov Haggai Maron Y. Lipman AI4CE 139 129 0 28 May 2019
Adversarially Robust Learning Could Leverage Computational HardnessInternational Conference on Algorithmic Learning Theory (ALT), 2019 Sanjam Garg S. Jha Saeed Mahloujifar Mohammad Mahmoody AAML 297 24 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