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

Title
Dynamic Defense Approach for Adversarial Robustness in Deep Neural Networks via Stochastic Ensemble Smoothed Model Ruoxi Qin Linyuan Wang Xing-yuan Chen Xuehui Du Bin Yan AAML 110 6 0 06 May 2021
Random Noise Defense Against Query-Based Black-Box AttacksNeural Information Processing Systems (NeurIPS), 2021 Zeyu Qin Yanbo Fan H. Zha Baoyuan Wu AAML 208 68 0 23 Apr 2021
Provable Robustness of Adversarial Training for Learning Halfspaces with NoiseInternational Conference on Machine Learning (ICML), 2021 Difan Zou Spencer Frei Quanquan Gu 135 14 0 19 Apr 2021
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?International Conference on Learning Representations (ICLR), 2021 Vikash Sehwag Saeed Mahloujifar Tinashe Handina Sihui Dai Chong Xiang M. Chiang Prateek Mittal OOD 202 144 0 19 Apr 2021
Simpler Certified Radius Maximization by Propagating CovariancesComputer Vision and Pattern Recognition (CVPR), 2021 Xingjian Zhen Rudrasis Chakraborty Vikas Singh AAML 94 5 0 13 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 268 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 230 29 0 30 Mar 2021
Certifiably-Robust Federated Adversarial Learning via Randomized SmoothingIEEE International Conference on Mobile Adhoc and Sensor Systems (MASS), 2021 Cheng Chen B. Kailkhura R. Goldhahn Yi Zhou AAML FedML 83 17 0 30 Mar 2021
Boosting Adversarial Transferability through Enhanced MomentumBritish Machine Vision Conference (BMVC), 2021 Xiaosen Wang Jiadong Lin Han Hu Jingdong Wang Kun He AAML 187 93 0 19 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
Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy Bronya R. Chernyak Bhiksha Raj Tamir Hazan Joseph Keshet AAML 103 2 0 15 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 156 34 0 15 Mar 2021
Constrained Learning with Non-Convex LossesIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2021 Luiz F. O. Chamon Santiago Paternain Miguel Calvo-Fullana Alejandro Ribeiro 262 52 0 08 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 236 8 0 07 Mar 2021
PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations Mark Niklas Muller Gleb Makarchuk Gagandeep Singh Markus Püschel Martin Vechev 258 109 0 05 Mar 2021
Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack Mengting Xu Tao Zhang Zhongnian Li Mingxia Liu Daoqiang Zhang AAML OOD MedIm 151 51 0 05 Mar 2021
PointGuard: Provably Robust 3D Point Cloud ClassificationComputer Vision and Pattern Recognition (CVPR), 2021 Hongbin Liu Jinyuan Jia Neil Zhenqiang Gong 3DPC 265 84 0 04 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
On the robustness of randomized classifiers to adversarial examplesMachine-mediated learning (ML), 2021 Rafael Pinot Laurent Meunier Florian Yger Cédric Gouy-Pailler Y. Chevaleyre Jamal Atif AAML 137 15 0 22 Feb 2021
A PAC-Bayes Analysis of Adversarial RobustnessNeural Information Processing Systems (NeurIPS), 2021 Paul Viallard Guillaume Vidot Amaury Habrard Emilie Morvant AAML 135 16 0 19 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
Globally-Robust Neural NetworksInternational Conference on Machine Learning (ICML), 2021 Klas Leino Zifan Wang Matt Fredrikson AAML OOD 264 144 0 16 Feb 2021
Certifiably Robust Variational AutoencodersInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Ben Barrett A. Camuto M. Willetts Tom Rainforth AAML DRL 193 16 0 15 Feb 2021
On the Paradox of Certified Training Nikola Jovanović Mislav Balunović Maximilian Baader Martin Vechev OOD 233 14 0 12 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 239 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 219 4 0 09 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 69 0 05 Feb 2021
Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression Masanori Yamada Sekitoshi Kanai Tomoharu Iwata Tomokatsu Takahashi Yuki Yamanaka Hiroshi Takahashi Atsutoshi Kumagai AAML 214 10 0 05 Feb 2021
Adversarially Robust Learning with Unknown Perturbation SetsAnnual Conference Computational Learning Theory (COLT), 2021 Omar Montasser Steve Hanneke Nathan Srebro AAML 151 28 0 03 Feb 2021
Admix: Enhancing the Transferability of Adversarial AttacksIEEE International Conference on Computer Vision (ICCV), 2021 Xiaosen Wang Xu He Jingdong Wang Kun He AAML 363 250 0 31 Jan 2021
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
Data-Dependent Randomized Smoothing Motasem Alfarra Adel Bibi Juil Sock Guohao Li UQCV 288 40 0 08 Dec 2020
Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection Byunggill Joe Jihun Hamm Sung Ju Hwang Sooel Son I. Shin AAML OOD 157 0 0 07 Dec 2020
Advocating for Multiple Defense Strategies against Adversarial Examples Alexandre Araujo Laurent Meunier Rafael Pinot Benjamin Négrevergne AAML 115 10 0 04 Dec 2020
How Robust are Randomized Smoothing based Defenses to Data Poisoning?Computer Vision and Pattern Recognition (CVPR), 2020 Akshay Mehra B. Kailkhura Pin-Yu Chen Jihun Hamm OOD AAML 267 33 0 02 Dec 2020
Adversarial Robustness Across Representation SpacesComputer Vision and Pattern Recognition (CVPR), 2020 Pranjal Awasthi George Yu Chun-Sung Ferng Andrew Tomkins Da-Cheng Juan OOD AAML 155 11 0 01 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
A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations Can Bakiskan Metehan Cekic Ahmet Dundar Sezer Upamanyu Madhow AAML 103 0 0 21 Nov 2020
Shaping Deep Feature Space towards Gaussian Mixture for Visual ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 Weitao Wan Jiansheng Chen Cheng Yu Tong Wu Yuanyi Zhong Ming-Hsuan Yang 116 9 0 18 Nov 2020
Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks Maungmaung Aprilpyone Hitoshi Kiya FedML 126 1 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 185 26 0 15 Nov 2020
Asymptotic Behavior of Adversarial Training in Binary Classification Hossein Taheri Ramtin Pedarsani Christos Thrampoulidis AAML 269 16 0 26 Oct 2020
Certified Distributional Robustness on Smoothed Classifiers Jungang Yang Liyao Xiang Pengzhi Chu Yukun Wang Cheng Zhou Xinbing Wang AAML 140 1 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
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial RobustnessProceedings of the IEEE (Proc. IEEE), 2020 Guillermo Ortiz-Jiménez Apostolos Modas Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 320 50 0 19 Oct 2020
Poisoned classifiers are not only backdoored, they are fundamentally broken Mingjie Sun Siddhant Agarwal J. Zico Kolter 241 26 0 18 Oct 2020
Higher-Order Certification for Randomized Smoothing Jeet Mohapatra Ching-Yun Ko Tsui-Wei Weng Pin-Yu Chen Sijia Liu Luca Daniel AAML 174 47 0 13 Oct 2020
Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples Sven Gowal Chongli Qin J. Uesato Timothy A. Mann Pushmeet Kohli AAML 407 357 0 07 Oct 2020
Adversarial Boot Camp: label free certified robustness in one epoch Ryan Campbell Chris Finlay Adam M. Oberman AAML 99 0 0 05 Oct 2020