Encrypted Vision Transformer

Encrypted Vision Transformers (EViT) explore methods to perform image analysis while preserving data privacy, primarily focusing on enhancing the robustness and efficiency of vision transformer architectures under various attack scenarios, including adversarial examples. Current research emphasizes developing encrypted models using techniques like random ensembles and self-supervised learning, often incorporating novel attention mechanisms to improve efficiency and accuracy. This field is significant for advancing secure and private image processing in cloud computing and other sensitive applications, addressing critical concerns about data security and privacy in the age of widespread AI deployment.

Papers

October 19, 2024

EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devices
Xin Li, Wenhui Zhu, Xuanzhao Dong, Oana M. Dumitrascu, Yalin Wang
Vision Transformer Transformer Based Medical Image Segmentation Based Approach CNN Model U Net U Shaped Network Convolutional Operation Efficient Vision Transformer Encrypted Vision Transformer

June 3, 2024

Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani, Charlie Rogers-Smith, Jeffrey Ladish, Christian Schroeder de Witt
Language Model Backdoor Attack State of the Art Robustness Encrypted Vision Transformer Backdoor Attacker

February 11, 2024

A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense
Ryota Iijima, Sayaka Shiota, Hitoshi Kiya
Vision Transformer Adversarial Example Adversarial Robustness White Box Encrypted Vision Transformer

October 10, 2023

EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
Yulong Shi, Mingwei Sun, Yongshuai Wang, Jiahao Ma, Zengqiang Chen
Vision Transformer Encrypted Vision Transformer

October 9, 2023

No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Xuwei Xu, Changlin Li, Yudong Chen, Xiaojun Chang, Jiajun Liu, Sen Wang
Vision Transformer Supervised ImageNet Computer Vision Task K TOKEN Image Token Efficient Vision Transformer Encrypted Vision Transformer

July 26, 2023

Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models
Ryota Iijima, Miki Tanaka, Sayaka Shiota, Hitoshi Kiya
Convolutional Neural Network Deep Neural Network Vision Transformer Adversarial Example Security Measure Encrypted Vision Transformer

January 5, 2023

Single-round Self-supervised Distributed Learning using Vision Transformer
Sangjoon Park, Ik-Jae Lee, Jun Won Kim, Jong Chul Ye
Deep Learning Vision Transformer Self Supervised Foundation Model Distributed Learning Multi Round Encrypted Vision Transformer

August 31, 2022

EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing
Qihua Feng, Peiya Li, Zhixun Lu, Chaozhuo Li, Zefang Wang, Zhiquan Liu, Chunhui Duan, Feiran Huang
Image Retrieval Cloud Computing Privacy Preserving Image Retrieval System Encrypted Vision Transformer World War II Era Cipher

Encrypted Vision Transformer

Papers

EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devices

Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits

A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense

EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention

No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling

Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models

Single-round Self-supervised Distributed Learning using Vision Transformer

EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing