Not All Prompts Are Secure: A Switchable Backdoor Attack Against
Pre-trained Vision Transformers

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers

17 May 2024

Kuofeng Gao

Yong-Liang Yang

Papers citing "Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers"

5 / 5 papers shown

Title
Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers Gorka Abad S. Picek Lorenzo Cavallaro A. Urbieta SILM 30 0 0 06 Sep 2024
Diversity-Aware Meta Visual Prompting Qidong Huang Xiaoyi Dong Dongdong Chen Weiming Zhang Feifei Wang Gang Hua Neng H. Yu VLM VPVLM 36 52 0 14 Mar 2023
AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition Shoufa Chen Chongjian Ge Zhan Tong Jiangliu Wang Yibing Song Jue Wang Ping Luo 138 631 0 26 May 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 258 7,337 0 11 Nov 2021
Poisoning the Unlabeled Dataset of Semi-Supervised Learning Nicholas Carlini AAML 136 65 0 04 May 2021