Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder

27 March 2023

Papers citing "Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder"

9 / 9 papers shown

Title
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming Y. Chen Shuo Shao Enhao Huang Yiming Li Pin-Yu Chen Z. Qin Kui Ren AAML 28 3 0 22 Feb 2025
CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification Fangwen Mu Junjie Wang Zhuohao Yu Lin Shi Song Wang Mingyang Li Qing Wang AAML 23 1 0 26 Oct 2024
Test-Time Backdoor Defense via Detecting and Repairing Jiyang Guan Jian Liang R. He AAML 15 0 0 11 Aug 2023
Black-box Backdoor Defense via Zero-shot Image Purification Yucheng Shi Mengnan Du Xuansheng Wu Zihan Guan Jin Sun Ninghao Liu 19 26 0 21 Mar 2023
Guided Diffusion Model for Adversarial Purification Jinyi Wang Zhaoyang Lyu Dahua Lin Bo Dai Hongfei Fu DiffM 177 77 0 30 May 2022
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning Zhenting Wang Juan Zhai Shiqing Ma AAML 110 97 0 26 May 2022
Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality Xiang Li Wenhai Wang Lingfeng Yang Jian Yang 95 73 0 20 May 2022
Diffusion Models for Adversarial Purification Weili Nie Brandon Guo Yujia Huang Chaowei Xiao Arash Vahdat Anima Anandkumar WIGM 184 410 0 16 May 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 255 7,337 0 11 Nov 2021