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"

50 / 389 papers shown

Title
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local SmoothingUSENIX Security Symposium (USENIX Security), 2023 Jiawei Zhang Zhongzhu Chen Huan Zhang Chaowei Xiao Yue Liu DiffM 182 32 0 28 Aug 2023
General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized SmoothingEuropean Conference on Artificial Intelligence (ECAI), 2023 Dmitrii Korzh Alireza Azadbakht Maryam Tahmasbi Alireza Javaheri AAML 166 0 0 17 Aug 2023
Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness Ruoxi Qin Linyuan Wang Xuehui Du Xing-yuan Chen Binghai Yan AAML 260 2 0 01 Aug 2023
Probabilistically robust conformal predictionConference on Uncertainty in Artificial Intelligence (UAI), 2023 Subhankar Ghosh Yuanjie Shi Taha Belkhouja Yan Yan J. Doppa Brian Jones AAML 265 27 0 31 Jul 2023
Learning Provably Robust Estimators for Inverse Problems via JitteringNeural Information Processing Systems (NeurIPS), 2023 Anselm Krainovic Mahdi Soltanolkotabi Reinhard Heckel OOD 102 9 0 24 Jul 2023
[Re] Double Sampling Randomized Smoothing A. Gupta Sarthak Gupta Abhay Kumar Harsh Dugar AAML 124 0 0 27 Jun 2023
Towards quantum enhanced adversarial robustness in machine learningNature Machine Intelligence (Nat. Mach. Intell.), 2023 Maxwell T. West S. Tsang J. S. Low C. Hill C. Leckie Lloyd C. L. Hollenberg S. Erfani Muhammad Usman AAML OOD 164 68 0 22 Jun 2023
Towards Better Certified Segmentation via Diffusion ModelsConference on Uncertainty in Artificial Intelligence (UAI), 2023 Othmane Laousy Alexandre Araujo G. Chassagnon M. Revel S. Garg Farshad Khorrami Maria Vakalopoulou DiffM 217 3 0 16 Jun 2023
Augment then Smooth: Reconciling Differential Privacy with Certified Robustness Jiapeng Wu Atiyeh Ashari Ghomi David Glukhov Jesse C. Cresswell Franziska Boenisch Nicolas Papernot AAML 223 4 0 14 Jun 2023
Expressive Losses for Verified Robustness via Convex CombinationsInternational Conference on Learning Representations (ICLR), 2023 Alessandro De Palma Rudy Bunel Krishnamurthy Dvijotham M. P. Kumar Robert Stanforth A. Lomuscio AAML 300 24 0 23 May 2023
Randomized Smoothing with Masked Inference for Adversarially Robust Text ClassificationsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Han Cheol Moon Shafiq Joty Ruochen Zhao Megh Thakkar Xu Chi AAML 191 18 0 11 May 2023
Understanding Noise-Augmented Training for Randomized Smoothing Ambar Pal Jeremias Sulam AAML 269 7 0 08 May 2023
TAPS: Connecting Certified and Adversarial TrainingNeural Information Processing Systems (NeurIPS), 2023 Yuhao Mao Mark Niklas Muller Marc Fischer Martin Vechev AAML 241 12 0 08 May 2023
Random Smoothing Regularization in Kernel Gradient Descent Learning Liang Ding Tianyang Hu Jiahan Jiang Donghao Li Wei Cao Xingtai Lv 200 8 0 05 May 2023
Certifying Ensembles: A General Certification Theory with S-LipschitznessInternational Conference on Machine Learning (ICML), 2023 Aleksandar Petrov Francisco Eiras Amartya Sanyal Juil Sock Adel Bibi UQCV 190 1 0 25 Apr 2023
Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser Astha Verma A. Subramanyam Siddhesh Bangar Naman Lal R. Shah Shiníchi Satoh 261 7 0 13 Apr 2023
A Certified Radius-Guided Attack Framework to Image Segmentation ModelsEuropean Symposium on Security and Privacy (Euro S&P), 2023 Wenjie Qu Youqi Li Binghui Wang AAML 128 5 0 05 Apr 2023
Provable Robustness for Streaming Models with a Sliding Window Aounon Kumar Vinu Sankar Sadasivan Soheil Feizi OOD AAML AI4TS 169 1 0 28 Mar 2023
Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection Nicola Franco Daniel Korth J. Lorenz Karsten Roscher Stephan Guennemann 132 6 0 27 Mar 2023
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified RobustnessInternational Conference on Learning Representations (ICLR), 2023 Shoumik Saha Wenxiao Wang Yigitcan Kaya Soheil Feizi Tudor Dumitras AAML 138 4 0 20 Mar 2023
Can Adversarial Examples Be Parsed to Reveal Victim Model Information?IEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 Yuguang Yao Jiancheng Liu Yifan Gong Xiaoming Liu Yanzhi Wang Xinyu Lin Sijia Liu AAML MLAU 222 1 0 13 Mar 2023
Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural NetworksComputer Vision and Pattern Recognition (CVPR), 2023 Binghui Wang Meng Pang Yun Dong AAML 124 17 0 10 Mar 2023
A Unified Algebraic Perspective on Lipschitz Neural NetworksInternational Conference on Learning Representations (ICLR), 2023 Alexandre Araujo Aaron J. Havens Blaise Delattre A. Allauzen Bin Hu AAML 224 60 0 06 Mar 2023
PointCert: Point Cloud Classification with Deterministic Certified Robustness GuaranteesComputer Vision and Pattern Recognition (CVPR), 2023 Jinghuai Zhang Jinyuan Jia Hongbin Liu Neil Zhenqiang Gong 3DPC 166 12 0 03 Mar 2023
Less is More: Data Pruning for Faster Adversarial Training Yize Li Pu Zhao Xinyu Lin B. Kailkhura Ryan Goldh AAML 237 14 0 23 Feb 2023
On the Role of Randomization in Adversarially Robust ClassificationNeural Information Processing Systems (NeurIPS), 2023 Lucas Gnecco-Heredia Y. Chevaleyre Benjamin Négrevergne Laurent Meunier Muni Sreenivas Pydi AAML 217 6 0 14 Feb 2023
Et Tu Certifications: Robustness Certificates Yield Better Adversarial ExamplesInternational Conference on Machine Learning (ICML), 2023 Andrew C. Cullen Shijie Liu Paul Montague S. Erfani Benjamin I. P. Rubinstein AAML 206 3 0 09 Feb 2023
Certified Robust Control under Adversarial PerturbationsAmerican Control Conference (ACC), 2023 Jinghan Yang Hunmin Kim Wenbin Wan N. Hovakimyan Yevgeniy Vorobeychik AAML 104 1 0 04 Feb 2023
Interpolation for Robust Learning: Data Augmentation on Wasserstein GeodesicsInternational Conference on Machine Learning (ICML), 2023 Jiacheng Zhu Jielin Qiu Aritra Guha Zhuolin Yang X. Nguyen Yue Liu Ding Zhao OOD 376 4 0 04 Feb 2023
Asymmetric Certified Robustness via Feature-Convex Neural NetworksNeural Information Processing Systems (NeurIPS), 2023 Samuel Pfrommer Brendon G. Anderson Julien Piet Somayeh Sojoudi AAML 209 9 0 03 Feb 2023
Towards Large Certified Radius in Randomized Smoothing using Quasiconcave OptimizationAAAI Conference on Artificial Intelligence (AAAI), 2023 Bo-Han Kung Shang-Tse Chen AAML 154 1 0 01 Feb 2023
RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized DeletionNeural Information Processing Systems (NeurIPS), 2023 Zhuoqun Huang Neil G. Marchant Keane Lucas Lujo Bauer O. Ohrimenko Benjamin I. P. Rubinstein AAML 307 20 0 31 Jan 2023
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive SmoothingSIAM Journal on Mathematics of Data Science (SIMODS), 2023 Yatong Bai Brendon G. Anderson Aerin Kim Somayeh Sojoudi AAML 325 22 0 29 Jan 2023
Unlocking Deterministic Robustness Certification on ImageNetNeural Information Processing Systems (NeurIPS), 2023 Kaiqin Hu Andy Zou Zifan Wang Klas Leino Matt Fredrikson OOD 323 15 0 29 Jan 2023
Explainability and Robustness of Deep Visual Classification Models Jindong Gu AAML 216 2 0 03 Jan 2023
Guidance Through Surrogate: Towards a Generic Diagnostic AttackIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022 Muzammal Naseer Salman Khan Fatih Porikli Fahad Shahbaz Khan AAML 132 1 0 30 Dec 2022
Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks Junlin Wu Hussein Sibai Yevgeniy Vorobeychik AAML 139 0 0 28 Dec 2022
Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement LearningAAAI Conference on Artificial Intelligence (AAAI), 2022 Ronghui Mu Wenjie Ruan Leandro Soriano Marcolino Gaojie Jin Q. Ni 238 7 0 22 Dec 2022
Confidence-aware Training of Smoothed Classifiers for Certified RobustnessAAAI Conference on Artificial Intelligence (AAAI), 2022 Jongheon Jeong Seojin Kim Jinwoo Shin AAML 323 10 0 18 Dec 2022
Alternating Objectives Generates Stronger PGD-Based Adversarial Attacks Nikolaos Antoniou Efthymios Georgiou Alexandros Potamianos AAML 161 5 0 15 Dec 2022
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning Hongbin Liu Wenjie Qu Jinyuan Jia Neil Zhenqiang Gong SSL 117 6 0 06 Dec 2022
Benchmarking Adversarially Robust Quantum Machine Learning at ScalePhysical Review Research (Phys. Rev. Res.), 2022 Maxwell T. West S. Erfani C. Leckie M. Sevior Lloyd C. L. Hollenberg Muhammad Usman AAML OOD 152 51 0 23 Nov 2022
Multi-head Ensemble of Smoothed Classifiers for Certified RobustnessNeural Networks (NN), 2022 Kun Fang Qinghua Tao Yingwen Wu Tao Li Xiaolin Huang Jie Yang AAML 130 2 0 20 Nov 2022
Improved techniques for deterministic l2 robustnessNeural Information Processing Systems (NeurIPS), 2022 Sahil Singla Soheil Feizi AAML 176 11 0 15 Nov 2022
Data Models for Dataset Drift Controls in Machine Learning With Optical Images Luis Oala Marco Aversa Gabriel Nobis Kurt Willis Yoan Neuenschwander ... E. Pomarico Wojciech Samek Roderick Murray-Smith Christoph Clausen B. Sanguinetti 270 6 0 04 Nov 2022
Instance-Dependent Generalization Bounds via Optimal TransportJournal of machine learning research (JMLR), 2022 Songyan Hou Parnian Kassraie Anastasis Kratsios Andreas Krause Jonas Rothfuss 435 11 0 02 Nov 2022
DensePure: Understanding Diffusion Models towards Adversarial Robustness Chaowei Xiao Zhongzhu Chen Kun Jin Zhenghao Hu Weili Nie Mingyan D. Liu Anima Anandkumar Yue Liu Basel Alomair DiffM 233 46 0 01 Nov 2022
Private and Reliable Neural Network InferenceConference on Computer and Communications Security (CCS), 2022 Nikola Jovanović Marc Fischer Samuel Steffen Martin Vechev 169 18 0 27 Oct 2022
Accelerating Certified Robustness Training via Knowledge TransferNeural Information Processing Systems (NeurIPS), 2022 Pratik Vaishnavi Kevin Eykholt Amir Rahmati 180 8 0 25 Oct 2022
Ares: A System-Oriented Wargame Framework for Adversarial ML Farhan Ahmed Pratik Vaishnavi Kevin Eykholt Amir Rahmati AAML 149 8 0 24 Oct 2022