On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

15 June 2020

Sabine Süsstrunk

Papers citing "On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them"

50 / 52 papers shown

Title
Momentum-SAM: Sharpness Aware Minimization without Computational Overhead Marlon Becker Frederick Altrock Benjamin Risse 105 6 0 22 Jan 2024
On the Convergence and Robustness of Adversarial Training Yisen Wang Xingjun Ma James Bailey Jinfeng Yi Bowen Zhou Quanquan Gu AAML 255 348 0 15 Dec 2021
Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness Pu Zhao Pin-Yu Chen Payel Das Karthikeyan N. Ramamurthy Xue Lin AAML 104 188 0 30 Apr 2020
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks Francesco Croce Matthias Hein AAML 209 1,835 0 03 Mar 2020
Overfitting in adversarially robust deep learning Leslie Rice Eric Wong Zico Kolter 92 800 0 26 Feb 2020
Fast is better than free: Revisiting adversarial training Eric Wong Leslie Rice J. Zico Kolter AAML OOD 134 1,175 0 12 Jan 2020
Square Attack: a query-efficient black-box adversarial attack via random search Maksym Andriushchenko Francesco Croce Nicolas Flammarion Matthias Hein AAML 68 983 0 29 Nov 2019
Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems Xingjun Ma Yuhao Niu Lin Gu Yisen Wang Yitian Zhao James Bailey Feng Lu MedIm AAML 65 448 0 24 Jul 2019
Towards Stable and Efficient Training of Verifiably Robust Neural Networks Huan Zhang Hongge Chen Chaowei Xiao Sven Gowal Robert Stanforth Yue Liu Duane S. Boning Cho-Jui Hsieh AAML 58 346 0 14 Jun 2019
Large Scale Structure of Neural Network Loss Landscapes Stanislav Fort Stanislaw Jastrzebski 44 83 0 11 Jun 2019
Intriguing properties of adversarial training at scale Cihang Xie Alan Yuille AAML 46 68 0 10 Jun 2019
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers Hadi Salman Greg Yang Jungshian Li Pengchuan Zhang Huan Zhang Ilya P. Razenshteyn Sébastien Bubeck AAML 64 547 0 09 Jun 2019
Unlabeled Data Improves Adversarial Robustness Y. Carmon Aditi Raghunathan Ludwig Schmidt Percy Liang John C. Duchi 119 752 0 31 May 2019
Are Labels Required for Improving Adversarial Robustness? J. Uesato Jean-Baptiste Alayrac Po-Sen Huang Robert Stanforth Alhussein Fawzi Pushmeet Kohli AAML 68 333 0 31 May 2019
Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models M. Singh Abhishek Sinha Nupur Kumari Harshitha Machiraju Balaji Krishnamurthy V. Balasubramanian AAML 40 61 0 13 May 2019
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle Dinghuai Zhang Tianyuan Zhang Yiping Lu Zhanxing Zhu Bin Dong AAML 96 360 0 02 May 2019
Adversarial Training for Free! Ali Shafahi Mahyar Najibi Amin Ghiasi Zheng Xu John P. Dickerson Christoph Studer L. Davis Gavin Taylor Tom Goldstein AAML 119 1,242 0 29 Apr 2019
Adversarial Robustness vs Model Compression, or Both? Shaokai Ye Kaidi Xu Sijia Liu Jan-Henrik Lambrechts Huan Zhang Aojun Zhou Kaisheng Ma Yanzhi Wang Xue Lin AAML 52 165 0 29 Mar 2019
Model Compression with Adversarial Robustness: A Unified Optimization Framework Shupeng Gui Haotao Wang Chen Yu Haichuan Yang Zhangyang Wang Ji Liu MQ 45 138 0 10 Feb 2019
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen Elan Rosenfeld J. Zico Kolter AAML 122 2,028 0 08 Feb 2019
An Investigation into Neural Net Optimization via Hessian Eigenvalue Density Behrooz Ghorbani Shankar Krishnan Ying Xiao ODL 60 322 0 29 Jan 2019
Using Pre-Training Can Improve Model Robustness and Uncertainty Dan Hendrycks Kimin Lee Mantas Mazeika NoLa 67 726 0 28 Jan 2019
On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models Sven Gowal Krishnamurthy Dvijotham Robert Stanforth Rudy Bunel Chongli Qin J. Uesato Relja Arandjelović Timothy A. Mann Pushmeet Kohli AAML 70 555 0 30 Oct 2018
A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation Akhilesh Deepak Gotmare N. Keskar Caiming Xiong R. Socher ODL 59 276 0 29 Oct 2018
Provable Robustness of ReLU networks via Maximization of Linear Regions Francesco Croce Maksym Andriushchenko Matthias Hein 63 166 0 17 Oct 2018
The jamming transition as a paradigm to understand the loss landscape of deep neural networks Mario Geiger S. Spigler Stéphane dÁscoli Levent Sagun Marco Baity-Jesi Giulio Biroli Matthieu Wyart 51 143 0 25 Sep 2018
Scaling provable adversarial defenses Eric Wong Frank R. Schmidt J. H. Metzen J. Zico Kolter AAML 64 446 0 31 May 2018
Adversarially Robust Generalization Requires More Data Ludwig Schmidt Shibani Santurkar Dimitris Tsipras Kunal Talwar Aleksander Madry OOD AAML 120 789 0 30 Apr 2018
Essentially No Barriers in Neural Network Energy Landscape Felix Dräxler K. Veschgini M. Salmhofer Fred Hamprecht MoMe 105 432 0 02 Mar 2018
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs T. Garipov Pavel Izmailov Dmitrii Podoprikhin Dmitry Vetrov A. Wilson UQCV 76 750 0 27 Feb 2018
Sensitivity and Generalization in Neural Networks: an Empirical Study Roman Novak Yasaman Bahri Daniel A. Abolafia Jeffrey Pennington Jascha Narain Sohl-Dickstein AAML 93 439 0 23 Feb 2018
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries Z. Yao A. Gholami Qi Lei Kurt Keutzer Michael W. Mahoney 61 167 0 22 Feb 2018
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples Anish Athalye Nicholas Carlini D. Wagner AAML 180 3,180 0 01 Feb 2018
Certified Defenses against Adversarial Examples Aditi Raghunathan Jacob Steinhardt Percy Liang AAML 103 968 0 29 Jan 2018
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey Naveed Akhtar Ajmal Mian AAML 69 1,863 0 02 Jan 2018
Visualizing the Loss Landscape of Neural Nets Hao Li Zheng Xu Gavin Taylor Christoph Studer Tom Goldstein 240 1,882 0 28 Dec 2017
Provable defenses against adversarial examples via the convex outer adversarial polytope Eric Wong J. Zico Kolter AAML 82 1,498 0 02 Nov 2017
Certifying Some Distributional Robustness with Principled Adversarial Training Aman Sinha Hongseok Namkoong Riccardo Volpi John C. Duchi OOD 99 862 0 29 Oct 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 255 12,023 0 19 Jun 2017
Snapshot Ensembles: Train 1, get M for free Gao Huang Yixuan Li Geoff Pleiss Zhuang Liu John E. Hopcroft Kilian Q. Weinberger OOD FedML UQCV 118 949 0 01 Apr 2017
Sharp Minima Can Generalize For Deep Nets Laurent Dinh Razvan Pascanu Samy Bengio Yoshua Bengio ODL 110 771 0 15 Mar 2017
Universal adversarial perturbations Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi Omar Fawzi P. Frossard AAML 125 2,525 0 26 Oct 2016
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 390 2,934 0 15 Sep 2016
Deep Learning without Poor Local Minima Kenji Kawaguchi ODL 190 923 0 23 May 2016
Gradient Descent Converges to Minimizers Jason D. Lee Max Simchowitz Michael I. Jordan Benjamin Recht 61 211 0 16 Feb 2016
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 1.7K 193,390 0 10 Dec 2015
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) Djork-Arné Clevert Thomas Unterthiner Sepp Hochreiter 263 5,517 0 23 Nov 2015
On the Quality of the Initial Basin in Overspecified Neural Networks Itay Safran Ohad Shamir 66 127 0 13 Nov 2015
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xinming Zhang Shaoqing Ren Jian Sun VLM 268 18,583 0 06 Feb 2015
Adam: A Method for Stochastic Optimization Diederik P. Kingma Jimmy Ba ODL 1.3K 149,820 0 22 Dec 2014