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
REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a ServiceNetwork and Distributed System Security Symposium (NDSS), 2023 Wenjie Qu Jinyuan Jia Neil Zhenqiang Gong SILM AAML 181 7 0 07 Jan 2023
Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks Junlin Wu Hussein Sibai Yevgeniy Vorobeychik AAML 155 0 0 28 Dec 2022
A Theoretical Study of The Effects of Adversarial Attacks on Sparse Regression Deepak Maurya Jean Honorio AAML 178 1 0 21 Dec 2022
The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results Mark Niklas Muller Christopher Brix Stanley Bak Changliu Liu Taylor T. Johnson NAI 264 52 0 20 Dec 2022
Confidence-aware Training of Smoothed Classifiers for Certified RobustnessAAAI Conference on Artificial Intelligence (AAAI), 2022 Jongheon Jeong Seojin Kim Jinwoo Shin AAML 351 10 0 18 Dec 2022
Probabilistic Verification of ReLU Neural Networks via Characteristic FunctionsConference on Learning for Dynamics & Control (L4DC), 2022 Joshua Pilipovsky Vignesh Sivaramakrishnan Meeko Oishi Panagiotis Tsiotras 306 9 0 03 Dec 2022
Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite RelaxationsInternational Conference on Machine Learning (ICML), 2022 Hong-Ming Chiu Richard Y. Zhang AAML 207 3 0 30 Nov 2022
Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural NetworksAAAI Conference on Artificial Intelligence (AAAI), 2022 Mathias Lechner Dorde Zikelic K. Chatterjee T. Henzinger Daniela Rus AAML 194 5 0 29 Nov 2022
Invariance-Aware Randomized Smoothing CertificatesNeural Information Processing Systems (NeurIPS), 2022 Jan Schuchardt Stephan Günnemann AAML 195 8 0 25 Nov 2022
BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval ArithmeticInternational Conference on Hybrid Systems: Computation and Control (HSCC), 2022 Wael Fatnassi Haitham Khedr Valen Yamamoto Yasser Shoukry 147 9 0 22 Nov 2022
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box AttackPattern Recognition (Pattern Recogn.), 2022 Yunfeng Diao He Wang Tianjia Shao Yong-Liang Yang Kun Zhou David C. Hogg Meng Wang AAML 148 11 0 21 Nov 2022
DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximation Yiting Wu Zhaodi Zhang Zhiyi Xue Si Liu Hao Fei AAML 165 0 0 21 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
Towards Robust Dataset Learning Yihan Wu Xinda Li Florian Kerschbaum Heng Huang Hongyang R. Zhang DD OOD 157 11 0 19 Nov 2022
VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from ScratchAAAI Conference on Artificial Intelligence (AAAI), 2022 Sawinder Kaur Yi Xiao Asif Salekin 256 0 0 17 Nov 2022
Improved techniques for deterministic l2 robustnessNeural Information Processing Systems (NeurIPS), 2022 Sahil Singla Soheil Feizi AAML 196 11 0 15 Nov 2022
Global Performance Guarantees for Neural Network Models of AC Power Flow Samuel C. Chevalier Spyros Chatzivasileiadis 165 8 0 14 Nov 2022
On Proper Learnability between Average- and Worst-case RobustnessNeural Information Processing Systems (NeurIPS), 2022 Vinod Raman Unique Subedi Ambuj Tewari 278 4 0 10 Nov 2022
Impact of Adversarial Training on Robustness and Generalizability of Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Enes Altinisik Hassan Sajjad Husrev Taha Sencar Safa Messaoud Sanjay Chawla AAML 164 15 0 10 Nov 2022
Visually Adversarial Attacks and Defenses in the Physical World: A Survey Xingxing Wei Bangzheng Pu Jiefan Lu Baoyuan Wu AAML 448 13 0 03 Nov 2022
On the Safety of Interpretable Machine Learning: A Maximum Deviation ApproachNeural Information Processing Systems (NeurIPS), 2022 Dennis L. Wei Rahul Nair Amit Dhurandhar Kush R. Varshney Elizabeth M. Daly Moninder Singh FAtt 192 10 0 02 Nov 2022
POLICE: Provably Optimal Linear Constraint Enforcement for Deep Neural NetworksIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 Randall Balestriero Yann LeCun 201 18 0 02 Nov 2022
The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial TrainingComputer Vision and Pattern Recognition (CVPR), 2022 Junhao Dong Seyed-Mohsen Moosavi-Dezfooli Jianhuang Lai Xiaohua Xie AAML 268 39 0 01 Nov 2022
FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs Yujia Huang I. D. Rodriguez Huan Zhang Yuanyuan Shi Yisong Yue 354 3 0 30 Oct 2022
Private and Reliable Neural Network InferenceConference on Computer and Communications Security (CCS), 2022 Nikola Jovanović Marc Fischer Samuel Steffen Martin Vechev 181 18 0 27 Oct 2022
Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection ClassesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Sina Baharlouei Fatemeh Sheikholeslami Meisam Razaviyayn Zico Kolter AAML 172 6 0 26 Oct 2022
Adversarial Purification with the Manifold HypothesisAAAI Conference on Artificial Intelligence (AAAI), 2022 Zhaoyuan Yang Zhiwei Xu Jing Zhang Leonid Sigal Peter Tu AAML 370 8 0 26 Oct 2022
Accelerating Certified Robustness Training via Knowledge TransferNeural Information Processing Systems (NeurIPS), 2022 Pratik Vaishnavi Kevin Eykholt Amir Rahmati 188 8 0 25 Oct 2022
Tighter Abstract Queries in Neural Network VerificationLogic Programming and Automated Reasoning (LPAR), 2022 Elazar Cohen Y. Elboher Clark W. Barrett Guy Katz 303 8 0 23 Oct 2022
Hindering Adversarial Attacks with Implicit Neural RepresentationsInternational Conference on Machine Learning (ICML), 2022 Andrei A. Rusu D. A. Calian Sven Gowal R. Hadsell AAML 324 5 0 22 Oct 2022
Learning Sample Reweighting for Accuracy and Adversarial Robustness Chester Holtz Tsui-Wei Weng Zhengchao Wan OOD 187 5 0 20 Oct 2022
DE-CROP: Data-efficient Certified Robustness for Pretrained ClassifiersIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2022 Gaurav Kumar Nayak Ruchit Rawal Anirban Chakraborty 189 3 0 17 Oct 2022
Zonotope Domains for Lagrangian Neural Network VerificationNeural Information Processing Systems (NeurIPS), 2022 Matt Jordan J. Hayase A. Dimakis Sewoong Oh 173 4 0 14 Oct 2022
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound PropagationNeural Information Processing Systems (NeurIPS), 2022 Zhouxing Shi Yihan Wang Huan Zhang Zico Kolter Cho-Jui Hsieh 353 54 0 13 Oct 2022
Visual Prompting for Adversarial RobustnessIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 Chenyi Zi P. Lorenz Yuguang Yao Pin-Yu Chen Sijia Liu VLM VPVLM 434 42 0 12 Oct 2022
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2022 Yongyuan Liang Yanchao Sun Ruijie Zheng Furong Huang OOD AAML OffRL 183 61 0 12 Oct 2022
Certified Training: Small Boxes are All You NeedInternational Conference on Learning Representations (ICLR), 2022 Mark Niklas Muller Franziska Eckert Marc Fischer Martin Vechev AAML 289 61 0 10 Oct 2022
Denoising Masked AutoEncoders Help Robust ClassificationInternational Conference on Learning Representations (ICLR), 2022 Quanlin Wu Hang Ye Yuntian Gu Huishuai Zhang Liwei Wang Di He 346 24 0 10 Oct 2022
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function PerspectiveNeural Information Processing Systems (NeurIPS), 2022 Bohang Zhang Du Jiang Di He Liwei Wang OOD 344 71 0 04 Oct 2022
Robustness Certification of Visual Perception Models via Camera Motion SmoothingConference on Robot Learning (CoRL), 2022 Hanjiang Hu Zuxin Liu Linyi Li Jiacheng Zhu Ding Zhao AAML 172 8 0 04 Oct 2022
MultiGuard: Provably Robust Multi-label Classification against Adversarial ExamplesNeural Information Processing Systems (NeurIPS), 2022 Jinyuan Jia Wenjie Qu Neil Zhenqiang Gong OOD 131 20 0 03 Oct 2022
On the tightness of linear relaxation based robustness certification methods Cheng Tang AAML 187 0 0 01 Oct 2022
Improving Robustness with Adaptive Weight DecayNeural Information Processing Systems (NeurIPS), 2022 Amin Ghiasi Ali Shafahi R. Ardekani OOD 201 13 0 30 Sep 2022
Robust Forecasting for Robotic Control: A Game-Theoretic ApproachIEEE International Conference on Robotics and Automation (ICRA), 2022 Shubhankar Agarwal David Fridovich-Keil Sandeep Chinchali AI4TS 249 4 0 22 Sep 2022
Unrestricted Adversarial Samples Based on Non-semantic Feature Clusters Substitution Ming-Kuai Zhou Xiaobing Pei AAML 130 0 0 31 Aug 2022
Unrestricted Black-box Adversarial Attack Using GAN with Limited Queries Dongbin Na Sangwoo Ji Jong Kim AAML 215 27 0 24 Aug 2022
A Novel Plug-and-Play Approach for Adversarially Robust Generalization Deepak Maurya Adarsh Barik Jean Honorio OOD AAML 228 0 0 19 Aug 2022
A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables Adrien Benamira Tristan Guérand Thomas Peyrin Trevor Yap Bryan Hooi 234 3 0 18 Aug 2022
An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models Brendon G. Anderson Tanmay Gautam Somayeh Sojoudi OOD 212 2 0 15 Aug 2022
General Cutting Planes for Bound-Propagation-Based Neural Network VerificationNeural Information Processing Systems (NeurIPS), 2022 Huan Zhang Shiqi Wang Kaidi Xu Linyi Li Yue Liu Suman Jana Cho-Jui Hsieh J. Zico Kolter 186 122 0 11 Aug 2022