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
Orthogonalizing Convolutional Layers with the Cayley TransformInternational Conference on Learning Representations (ICLR), 2021 Asher Trockman J. Zico Kolter 190 126 0 14 Apr 2021
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition Alessandro De Palma Rudy Bunel Alban Desmaison Krishnamurthy Dvijotham Pushmeet Kohli Juil Sock M. P. Kumar 169 58 0 14 Apr 2021
Simpler Certified Radius Maximization by Propagating CovariancesComputer Vision and Pattern Recognition (CVPR), 2021 Xingjian Zhen Rudrasis Chakraborty Vikas Singh AAML 114 5 0 13 Apr 2021
Relating Adversarially Robust Generalization to Flat MinimaIEEE International Conference on Computer Vision (ICCV), 2021 David Stutz Matthias Hein Bernt Schiele OOD 251 78 0 09 Apr 2021
A Review of Formal Methods applied to Machine Learning Caterina Urban Antoine Miné 256 68 0 06 Apr 2021
$Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model$ Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture ModelSIAM Journal on Mathematics of Data Science (SIMODS), 2021 Payam Delgosha Hamed Hassani Ramtin Pedarsani AAML 148 8 0 05 Apr 2021
Reliably fast adversarial training via latent adversarial perturbationIEEE International Conference on Computer Vision (ICCV), 2021 Geon Yeong Park Sang Wan Lee AAML 160 33 0 04 Apr 2021
Towards Evaluating and Training Verifiably Robust Neural NetworksComputer Vision and Pattern Recognition (CVPR), 2021 Zhaoyang Lyu Minghao Guo Tong Wu Guodong Xu Kehuan Zhang Dahua Lin AAML 231 24 0 01 Apr 2021
Domain Invariant Adversarial Learning Matan Levi Idan Attias A. Kontorovich AAML OOD 453 12 0 01 Apr 2021
Fast Certified Robust Training with Short WarmupNeural Information Processing Systems (NeurIPS), 2021 Zhouxing Shi Yihan Wang Huan Zhang Jinfeng Yi Cho-Jui Hsieh AAML 280 66 0 31 Mar 2021
Robustness Certification for Point Cloud ModelsIEEE International Conference on Computer Vision (ICCV), 2021 Tobias Lorenz Anian Ruoss Mislav Balunović Gagandeep Singh Martin Vechev 3DPC 234 29 0 30 Mar 2021
Recent Advances in Large Margin LearningIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 Yiwen Guo Changshui Zhang AAML AI4CE 260 18 0 25 Mar 2021
Towards Both Accurate and Robust Neural Networks without Extra DataInternational Conference on Artificial Neural Networks (ICANN), 2021 Faqiang Liu Rong Zhao AAML 103 1 0 24 Mar 2021
$Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces$ Improved Estimation of Concentration Under $\ell_p$ -Norm Distance Metrics Using Half SpacesInternational Conference on Learning Representations (ICLR), 2021 Jack Prescott Xiao Zhang David Evans 119 5 0 24 Mar 2021
NNrepair: Constraint-based Repair of Neural Network ClassifiersInternational Conference on Computer Aided Verification (CAV), 2021 Muhammad Usman D. Gopinath Youcheng Sun Yannic Noller C. Păsăreanu 130 45 0 23 Mar 2021
Performance Bounds for Neural Network Estimators: Applications in Fault DetectionAmerican Control Conference (ACC), 2021 Navid Hashemi Mahyar Fazlyab Justin Ruths AAML 115 3 0 22 Mar 2021
Robust Models Are More Interpretable Because Attributions Look NormalInternational Conference on Machine Learning (ICML), 2021 Zifan Wang Matt Fredrikson Anupam Datta OOD FAtt 278 31 0 20 Mar 2021
Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition Yaodong Yu Zitong Yang Guang Cheng Jacob Steinhardt Yi-An Ma 238 19 0 17 Mar 2021
Improved, Deterministic Smoothing for L_1 Certified RobustnessInternational Conference on Machine Learning (ICML), 2021 Alexander Levine Soheil Feizi AAML 231 47 0 17 Mar 2021
Adversarial Training is Not Ready for Robot LearningIEEE International Conference on Robotics and Automation (ICRA), 2021 Mathias Lechner Ramin Hasani Radu Grosu Daniela Rus T. Henzinger AAML 164 34 0 15 Mar 2021
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness VerificationNeural Information Processing Systems (NeurIPS), 2021 Shiqi Wang Huan Zhang Kaidi Xu Xue Lin Suman Jana Cho-Jui Hsieh Zico Kolter 283 255 0 11 Mar 2021
Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracy Chong Chen Kezhi Kong Peihong Yu J. Luque Tom Goldstein Furong Huang AAML 240 8 0 07 Mar 2021
A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness Jacob D. Abernethy Pranjal Awasthi Satyen Kale AAML 145 6 0 01 Mar 2021
Explaining Adversarial Vulnerability with a Data Sparsity HypothesisNeurocomputing (Neurocomputing), 2021 Mahsa Paknezhad Cuong Phuc Ngo Amadeus Aristo Winarto Alistair Cheong Beh Chuen Yang Wu Jiayang Lee Hwee Kuan OOD AAML 244 10 0 01 Mar 2021
Towards Robust and Reliable Algorithmic RecourseNeural Information Processing Systems (NeurIPS), 2021 Sohini Upadhyay Shalmali Joshi Himabindu Lakkaraju 203 121 0 26 Feb 2021
Adversarial Robustness with Non-uniform PerturbationsNeural Information Processing Systems (NeurIPS), 2021 Ece Naz Erdemir Jeffrey Bickford Luca Melis Sergul Aydore AAML 221 32 0 24 Feb 2021
Model-Based Domain GeneralizationNeural Information Processing Systems (NeurIPS), 2021 Avi Schwarzschild George J. Pappas Hamed Hassani OOD 295 148 0 23 Feb 2021
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningInternational Conference on Learning Representations (ICLR), 2021 Ren Wang Kaidi Xu Sijia Liu Pin-Yu Chen Tsui-Wei Weng Chuang Gan Meng Wang AAML 246 53 0 20 Feb 2021
Center Smoothing: Certified Robustness for Networks with Structured OutputsNeural Information Processing Systems (NeurIPS), 2021 Aounon Kumar Tom Goldstein OOD AAML UQCV 205 20 0 19 Feb 2021
Bridging the Gap Between Adversarial Robustness and Optimization Bias Fartash Faghri Sven Gowal C. N. Vasconcelos David J. Fleet Fabian Pedregosa Nicolas Le Roux AAML 371 8 0 17 Feb 2021
Adversarially Robust Kernel SmoothingInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Jia-Jie Zhu Christina Kouridi Yassine Nemmour Bernhard Schölkopf 226 8 0 16 Feb 2021
Globally-Robust Neural NetworksInternational Conference on Machine Learning (ICML), 2021 Klas Leino Zifan Wang Matt Fredrikson AAML OOD 272 144 0 16 Feb 2021
Low Curvature Activations Reduce Overfitting in Adversarial TrainingIEEE International Conference on Computer Vision (ICCV), 2021 Vasu Singla Sahil Singla David Jacobs Soheil Feizi AAML 212 49 0 15 Feb 2021
Generating Structured Adversarial Attacks Using Frank-Wolfe Method Ehsan Kazemi Thomas Kerdreux Liquang Wang AAML DiffM 141 1 0 15 Feb 2021
Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPSIEEE Communications Surveys and Tutorials (COMST), 2021 Felix O. Olowononi D. Rawat Chunmei Liu 275 159 0 14 Feb 2021
On the Paradox of Certified Training Nikola Jovanović Mislav Balunović Maximilian Baader Martin Vechev OOD 233 14 0 12 Feb 2021
Adversarial Robustness: What fools you makes you stronger Grzegorz Gluch R. Urbanke AAML 200 2 0 10 Feb 2021
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist NeuronsInternational Conference on Machine Learning (ICML), 2021 Bohang Zhang Tianle Cai Zhou Lu Di He Liwei Wang OOD 247 56 0 10 Feb 2021
Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples Jay Nandy Sudipan Saha Wynne Hsu Yang Deng Xiaosu Zhu AAML 227 4 0 09 Feb 2021
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial TrainingNeural Information Processing Systems (NeurIPS), 2021 Lue Tao Lei Feng Jinfeng Yi Sheng-Jun Huang Songcan Chen AAML 411 81 0 09 Feb 2021
Partition-based formulations for mixed-integer optimization of trained ReLU neural networksNeural Information Processing Systems (NeurIPS), 2021 Calvin Tsay Jan Kronqvist Alexander Thebelt Ruth Misener 201 77 0 08 Feb 2021
Efficient Certified Defenses Against Patch Attacks on Image ClassifiersInternational Conference on Learning Representations (ICLR), 2021 J. H. Metzen Maksym Yatsura AAML 107 48 0 08 Feb 2021
Adversarial Imaging PipelinesComputer Vision and Pattern Recognition (CVPR), 2021 Buu Phan Fahim Mannan Felix Heide AAML 162 28 0 07 Feb 2021
DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding AttacksConference on Computer and Communications Security (CCS), 2021 Chong Xiang Prateek Mittal AAML 216 70 0 05 Feb 2021
Adversarially Robust Learning with Unknown Perturbation SetsAnnual Conference Computational Learning Theory (COLT), 2021 Omar Montasser Steve Hanneke Nathan Srebro AAML 159 28 0 03 Feb 2021
Generative deep learning for decision making in gas networksMathematical Methods of Operations Research (MMOR), 2021 Lovis Anderson Mark Turner T. Koch AI4CE 137 8 0 03 Feb 2021
Fast Training of Provably Robust Neural Networks by SinglePropAAAI Conference on Artificial Intelligence (AAAI), 2021 Akhilan Boopathy Tsui-Wei Weng Sijia Liu Pin-Yu Chen Gaoyuan Zhang Luca Daniel AAML 152 7 0 01 Feb 2021
Adversarial Learning with Cost-Sensitive ClassesIEEE Transactions on Cybernetics (IEEE Trans. Cybern.), 2021 Hao Shen Sihong Chen Ran Wang Xizhao Wang AAML 132 11 0 29 Jan 2021
Increasing the Confidence of Deep Neural Networks by Coverage AnalysisIEEE Transactions on Software Engineering (TSE), 2021 Giulio Rossolini Alessandro Biondi Giorgio Buttazzo AAML 248 20 0 28 Jan 2021
Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification Brendon G. Anderson Ziye Ma Jingqi Li Somayeh Sojoudi 482 1 0 22 Jan 2021