v1v2 (latest)

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

21 June 2024

Xianlong Wang

Shengshan Hu

Yechao Zhang

Ziqi Zhou

Leo Yu Zhang

Peng Xu

Wei Wan

Hai Jin

AAML

ArXiv (abs)PDF HTML Github (4★)

Papers citing "ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification"

26 / 26 papers shown

Title
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples Ziqi Zhou Minghui Li Wei Liu Shengshan Hu Yechao Zhang Wei Wan Lulu Xue Leo Yu Zhang Dezhong Yao Hai Jin SILM AAML 94 10 0 16 Mar 2024
Why Does Little Robustness Help? Understanding and Improving Adversarial Transferability from Surrogate Training Yechao Zhang Shengshan Hu Leo Yu Zhang Junyu Shi Minghui Li Xiaogeng Liu Wei Wan Hai Jin AAML 105 23 0 15 Jul 2023
The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models H. M. Dolatabadi S. Erfani C. Leckie DiffM 95 18 0 15 Mar 2023
CUDA: Convolution-based Unlearnable Datasets Vinu Sankar Sadasivan Mahdi Soltanolkotabi Soheil Feizi MU 53 25 0 07 Mar 2023
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors Sizhe Chen Geng Yuan Xinwen Cheng Yifan Gong Minghai Qin Yanzhi Wang Xiaolin Huang AAML 62 20 0 22 Nov 2022
Transferable Unlearnable Examples Jie Ren Han Xu Yuxuan Wan Xingjun Ma Lichao Sun Jiliang Tang 83 36 0 18 Oct 2022
Autoregressive Perturbations for Data Poisoning Pedro Sandoval-Segura Vasu Singla Jonas Geiping Micah Goldblum Tom Goldstein David Jacobs AAML 73 41 0 08 Jun 2022
Diffusion Models for Adversarial Purification Weili Nie Brandon Guo Yujia Huang Chaowei Xiao Arash Vahdat Anima Anandkumar WIGM 263 444 0 16 May 2022
Poisons that are learned faster are more effective Pedro Sandoval-Segura Vasu Singla Liam H. Fowl Jonas Geiping Micah Goldblum David Jacobs Tom Goldstein 62 17 0 19 Apr 2022
Availability Attacks Create Shortcuts Da Yu Huishuai Zhang Wei Chen Jian Yin Tie-Yan Liu AAML 96 58 0 01 Nov 2021
Adversarial Examples Make Strong Poisons Liam H. Fowl Micah Goldblum Ping Yeh-Chiang Jonas Geiping Wojtek Czaja Tom Goldstein SILM 85 135 0 21 Jun 2021
Improved Denoising Diffusion Probabilistic Models Alex Nichol Prafulla Dhariwal DiffM 349 3,702 0 18 Feb 2021
Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release Liam H. Fowl Ping Yeh-Chiang Micah Goldblum Jonas Geiping Arpit Bansal W. Czaja Tom Goldstein 60 43 0 16 Feb 2021
Maximum Likelihood Training of Score-Based Diffusion Models Yang Song Conor Durkan Iain Murray Stefano Ermon DiffM 160 670 0 22 Jan 2021
Unlearnable Examples: Making Personal Data Unexploitable Hanxun Huang Xingjun Ma S. Erfani James Bailey Yisen Wang MIACV 234 193 0 13 Jan 2021
Score-Based Generative Modeling through Stochastic Differential Equations Yang Song Jascha Narain Sohl-Dickstein Diederik P. Kingma Abhishek Kumar Stefano Ermon Ben Poole DiffM SyDa 344 6,480 0 26 Nov 2020
Shortcut Learning in Deep Neural Networks Robert Geirhos J. Jacobsen Claudio Michaelis R. Zemel Wieland Brendel Matthias Bethge Felix Wichmann 209 2,052 0 16 Apr 2020
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping Sanghyun Hong Varun Chandrasekaran Yigitcan Kaya Tudor Dumitras Nicolas Papernot AAML 82 136 0 26 Feb 2020
Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder Ji Feng Qi-Zhi Cai Zhi Zhou AAML 58 105 0 22 May 2019
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features Sangdoo Yun Dongyoon Han Seong Joon Oh Sanghyuk Chun Junsuk Choe Y. Yoo OOD 620 4,780 0 13 May 2019
mixup: Beyond Empirical Risk Minimization Hongyi Zhang Moustapha Cissé Yann N. Dauphin David Lopez-Paz NoLa 280 9,764 0 25 Oct 2017
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization Luis Muñoz-González Battista Biggio Ambra Demontis Andrea Paudice Vasin Wongrassamee Emil C. Lupu Fabio Roli AAML 99 633 0 29 Aug 2017
Improved Regularization of Convolutional Neural Networks with Cutout Terrance Devries Graham W. Taylor 117 3,765 0 15 Aug 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 310 12,069 0 19 Jun 2017
Densely Connected Convolutional Networks Gao Huang Zhuang Liu Laurens van der Maaten Kilian Q. Weinberger PINN 3DV 775 36,813 0 25 Aug 2016
Very Deep Convolutional Networks for Large-Scale Image Recognition Karen Simonyan Andrew Zisserman FAtt MDE 1.7K 100,386 0 04 Sep 2014