v1v2v3 (latest)

Towards Stable Backdoor Purification through Feature Shift Tuning

3 October 2023

Rui Min

Zeyu Qin

Li Shen

Minhao Cheng

AAML

ArXiv (abs)PDF HTML Github (26★)

Papers citing "Towards Stable Backdoor Purification through Feature Shift Tuning"

22 / 22 papers shown

Title
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning Zhifang Zhang Shuo He Bingquan Shen Lei Feng Lei Feng AAML 131 1 0 29 Dec 2024
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning Baoyuan Wu Hongrui Chen Ruotong Wang Zihao Zhu Shaokui Wei Danni Yuan Chaoxiao Shen ELM AAML 120 145 0 25 Jun 2022
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning Lin Zhang Li Shen Liang Ding Dacheng Tao Ling-Yu Duan FedML 88 267 0 17 Mar 2022
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution Ananya Kumar Aditi Raghunathan Robbie Jones Tengyu Ma Percy Liang OODD 132 685 0 21 Feb 2022
Backdoor Defense via Decoupling the Training Process Kunzhe Huang Yiming Li Baoyuan Wu Zhan Qin Kui Ren AAML FedML 60 194 0 05 Feb 2022
Combined Scaling for Zero-shot Transfer Learning Hieu H. Pham Zihang Dai Golnaz Ghiasi Kenji Kawaguchi Hanxiao Liu ... Yi-Ting Chen Minh-Thang Luong Yonghui Wu Mingxing Tan Quoc V. Le VLM 90 200 0 19 Nov 2021
Anti-Backdoor Learning: Training Clean Models on Poisoned Data Yige Li X. Lyu Nodens Koren Lingjuan Lyu Yue Liu Xingjun Ma OnRL 93 336 0 22 Oct 2021
Adversarial Unlearning of Backdoors via Implicit Hypergradient Yi Zeng Si-An Chen Won Park Z. Morley Mao Ming Jin R. Jia AAML 131 178 0 07 Oct 2021
Finetuned Language Models Are Zero-Shot Learners Jason W. Wei Maarten Bosma Vincent Zhao Kelvin Guu Adams Wei Yu Brian Lester Nan Du Andrew M. Dai Quoc V. Le ALM UQCV 256 3,789 0 03 Sep 2021
Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization John Miller Rohan Taori Aditi Raghunathan Shiori Sagawa Pang Wei Koh Vaishaal Shankar Percy Liang Y. Carmon Ludwig Schmidt OODD OOD 112 278 0 09 Jul 2021
Poisoning and Backdooring Contrastive Learning Nicholas Carlini Andreas Terzis 68 166 0 17 Jun 2021
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Ze Liu Yutong Lin Yue Cao Han Hu Yixuan Wei Zheng Zhang Stephen Lin B. Guo ViT 470 21,603 0 25 Mar 2021
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum Dimitris Tsipras Chulin Xie Xinyun Chen Avi Schwarzschild Basel Alomair Aleksander Madry Yue Liu Tom Goldstein SILM 114 282 0 18 Dec 2020
Invisible Backdoor Attack with Sample-Specific Triggers Yuezun Li Yiming Li Baoyuan Wu Longkang Li Ran He Siwei Lyu AAML DiffM 106 492 0 07 Dec 2020
Input-Aware Dynamic Backdoor Attack A. Nguyen Anh Tran AAML 80 433 0 16 Oct 2020
A Simple Framework for Contrastive Learning of Visual Representations Ting-Li Chen Simon Kornblith Mohammad Norouzi Geoffrey E. Hinton SSL 398 18,897 0 13 Feb 2020
Label-Consistent Backdoor Attacks Alexander Turner Dimitris Tsipras Aleksander Madry AAML 79 389 0 05 Dec 2019
Bypassing Backdoor Detection Algorithms in Deep Learning T. Tan Reza Shokri FedML AAML 99 152 0 31 May 2019
A new Backdoor Attack in CNNs by training set corruption without label poisoning Mauro Barni Kassem Kallas B. Tondi AAML 122 360 0 12 Feb 2019
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning Xinyun Chen Chang-rui Liu Yue Liu Kimberly Lu Basel Alomair AAML SILM 146 1,860 0 15 Dec 2017
A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets P. Chrabaszcz I. Loshchilov Frank Hutter SSeg OOD 177 649 0 27 Jul 2017
Densely Connected Convolutional Networks Gao Huang Zhuang Liu Laurens van der Maaten Kilian Q. Weinberger PINN 3DV 865 36,910 0 25 Aug 2016