v1v2 (latest)

Understanding and Improving Fast Adversarial Training

6 July 2020

Maksym Andriushchenko

Nicolas Flammarion

AAML

ArXiv (abs)PDF HTML Github (95★)

Papers citing "Understanding and Improving Fast Adversarial Training"

50 / 193 papers shown

Title
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks Jianan Zhou Jianing Zhu Jingfeng Zhang Tongliang Liu Gang Niu Bo Han Masashi Sugiyama AAML 45 9 0 01 Nov 2022
AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient F. Nikfam Alberto Marchisio Maurizio Martina Mohamed Bennai AAML 53 0 0 13 Oct 2022
Robust Models are less Over-Confident Julia Grabinski Paul Gavrikov J. Keuper Margret Keuper AAML 80 25 0 12 Oct 2022
Stable and Efficient Adversarial Training through Local Linearization Zhuorong Li Daiwei Yu AAML 32 0 0 11 Oct 2022
Adversarial Coreset Selection for Efficient Robust Training H. M. Dolatabadi S. Erfani C. Leckie AAML 75 9 0 13 Sep 2022
FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices Minxue Tang Jianyi Zhang Mingyuan Ma Louis DiValentin Aolin Ding Amin Hassanzadeh H. Li Yiran Chen FedML 75 0 0 08 Sep 2022
Bag of Tricks for FGSM Adversarial Training Zichao Li Li Liu Zeyu Wang Yuyin Zhou Cihang Xie AAML 64 6 0 06 Sep 2022
Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training Zihui Wu Haichang Gao Bingqian Zhou Xiaoyan Guo Shudong Zhang AAML 56 0 0 26 Aug 2022
Adversarial Vulnerability of Temporal Feature Networks for Object Detection Svetlana Pavlitskaya Nikolai Polley Michael Weber J. Marius Zöllner AAML 63 3 0 23 Aug 2022
Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance Bahjat Kawar Roy Ganz Michael Elad DiffM 91 39 0 18 Aug 2022
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness Jindong Gu Hengshuang Zhao Volker Tresp Philip Torr AAML 119 77 0 25 Jul 2022
Do Perceptually Aligned Gradients Imply Adversarial Robustness? Roy Ganz Bahjat Kawar Michael Elad AAML 45 10 0 22 Jul 2022
Towards Efficient Adversarial Training on Vision Transformers Boxi Wu Jindong Gu Zhifeng Li Deng Cai Xiaofei He Wei Liu ViT AAML 94 40 0 21 Jul 2022
Prior-Guided Adversarial Initialization for Fast Adversarial Training Xiaojun Jia Yong Zhang Xingxing Wei Baoyuan Wu Ke Ma Jue Wang Xiaochun Cao AAML 63 40 0 18 Jul 2022
Understanding Robust Learning through the Lens of Representation Similarities Christian Cianfarani A. Bhagoji Vikash Sehwag Ben Y. Zhao Prateek Mittal Haitao Zheng OOD 81 16 0 20 Jun 2022
Catastrophic overfitting can be induced with discriminative non-robust features Guillermo Ortiz-Jiménez Pau de Jorge Amartya Sanyal Adel Bibi P. Dokania P. Frossard Grégory Rogez Philip Torr AAML 61 3 0 16 Jun 2022
Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness Tianlong Chen Huan Zhang Zhenyu Zhang Shiyu Chang Sijia Liu Pin-Yu Chen Zhangyang Wang AAML 63 11 0 15 Jun 2022
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack Ruize Gao Jiongxiao Wang Kaiwen Zhou Feng Liu Binghui Xie Gang Niu Bo Han James Cheng AAML 48 15 0 15 Jun 2022
Can pruning improve certified robustness of neural networks? Zhangheng Li Tianlong Chen Linyi Li Yue Liu Zhangyang Wang AAML 108 13 0 15 Jun 2022
Distributed Adversarial Training to Robustify Deep Neural Networks at Scale Gaoyuan Zhang Songtao Lu Yihua Zhang Xiangyi Chen Pin-Yu Chen Quanfu Fan Lee Martie L. Horesh Min-Fong Hong Sijia Liu OOD 73 12 0 13 Jun 2022
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training Tianlong Chen Zhenyu Zhang Sijia Liu Yang Zhang Shiyu Chang Zhangyang Wang AAML 74 8 0 09 Jun 2022
Fast Adversarial Training with Adaptive Step Size Zhichao Huang Yanbo Fan Chen Liu Weizhong Zhang Yong Zhang Mathieu Salzmann Sabine Süsstrunk Jue Wang AAML 79 33 0 06 Jun 2022
On Trace of PGD-Like Adversarial Attacks Mo Zhou Vishal M. Patel AAML 75 4 0 19 May 2022
How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations? Alvin Chan Yew-Soon Ong Clement Tan AAML 60 14 0 09 May 2022
A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges Zhenghua Chen Min-man Wu Alvin Chan Xiaoli Li Yew-Soon Ong 49 7 0 08 May 2022
Rethinking Classifier and Adversarial Attack Youhuan Yang Lei Sun Leyu Dai Song Guo Xiuqing Mao Xiaoqin Wang Bayi Xu AAML 55 0 0 04 May 2022
CE-based white-box adversarial attacks will not work using super-fitting Youhuan Yang Lei Sun Leyu Dai Song Guo Xiuqing Mao Xiaoqin Wang Bayi Xu AAML 104 0 0 04 May 2022
Fast AdvProp Jieru Mei Yucheng Han Yutong Bai Yixiao Zhang Yingwei Li Xianhang Li Alan Yuille Cihang Xie AAML 85 8 0 21 Apr 2022
Adversarial Robustness through the Lens of Convolutional Filters Paul Gavrikov J. Keuper 70 15 0 05 Apr 2022
FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting Julia Grabinski Steffen Jung J. Keuper Margret Keuper AAML 73 22 0 01 Apr 2022
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters Paul Gavrikov J. Keuper AAML 105 31 0 29 Mar 2022
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective Yimeng Zhang Yuguang Yao Jinghan Jia Jinfeng Yi Min-Fong Hong Shiyu Chang Sijia Liu AAML 126 34 0 27 Mar 2022
A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies Zhuang Qian Kaizhu Huang Qiufeng Wang Xu-Yao Zhang OOD AAML ObjD 128 73 0 26 Mar 2022
Task-Agnostic Robust Representation Learning A. Nguyen Ser Nam Lim Philip Torr SSL OOD 18 4 0 15 Mar 2022
On the benefits of knowledge distillation for adversarial robustness Javier Maroto Guillermo Ortiz-Jiménez P. Frossard AAML FedML 72 20 0 14 Mar 2022
Adversarial amplitude swap towards robust image classifiers Tan Yang K. Kawamoto Hiroshi Kera AAML 40 1 0 14 Mar 2022
Why adversarial training can hurt robust accuracy Jacob Clarysse Julia Hörrmann Fanny Yang AAML 43 19 0 03 Mar 2022
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses Francesco Croce Sven Gowal T. Brunner Evan Shelhamer Matthias Hein A. Cemgil TTA AAML 237 70 0 28 Feb 2022
ARIA: Adversarially Robust Image Attribution for Content Provenance Maksym Andriushchenko Xiaochen Li Geoffrey Oxholm Thomas Gittings Tu Bui Nicolas Flammarion John Collomosse AAML 44 2 0 25 Feb 2022
Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness Beomsu Kim Junghoon Seo AAML 100 0 0 21 Feb 2022
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition Tianyu Pang Min Lin Xiao Yang Junyi Zhu Shuicheng Yan 120 124 0 21 Feb 2022
The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retraining Murat Kuzlu Ferhat Ozgur Catak Umit Cali Evren Çatak Ozgur Guler AAML 58 9 0 16 Feb 2022
Random Walks for Adversarial Meshes Amir Belder Gal Yefet Ran Ben Izhak A. Tal AAML 76 2 0 15 Feb 2022
Improving Generalization via Uncertainty Driven Perturbations Matteo Pagliardini Gilberto Manunza Martin Jaggi Michael I. Jordan Tatjana Chavdarova AAML AI4CE 78 4 0 11 Feb 2022
Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign Axi Niu Kang Zhang Chaoning Zhang Chenshuang Zhang In So Kweon Chang D. Yoo Yanning Zhang AAML 80 6 0 11 Feb 2022
Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework Mohammad Khalooei M. Homayounpour M. Amirmazlaghani AAML 63 3 0 05 Feb 2022
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training Pau de Jorge Adel Bibi Riccardo Volpi Amartya Sanyal Philip Torr Grégory Rogez P. Dokania AAML 118 47 0 02 Feb 2022
Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses Mengting Xu Tao Zhang Zhongnian Li Daoqiang Zhang AAML 69 1 0 29 Jan 2022
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization Yihua Zhang Guanhua Zhang Prashant Khanduri Min-Fong Hong Shiyu Chang Sijia Liu AAML 102 89 0 23 Dec 2021
$$\ell_\infty$-Robustness and Beyond: Unleashing Efficient Adversarial Training$ $\ell_\infty$ -Robustness and Beyond: Unleashing Efficient Adversarial Training H. M. Dolatabadi S. Erfani C. Leckie OOD AAML 92 12 0 01 Dec 2021