追蹤
Zeyang Sha
Zeyang Sha
CISPA Helmholtz Center for Information Security
在 cispa.de 的電子郵件地址已通過驗證 - 首頁
標題
引用次數
引用次數
年份
DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Diffusion Models
Z Sha, Z Li, N Yu, Y Zhang
ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022
66*2022
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Z Sha, X He, N Yu, M Backes, Y Zhang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
232022
Fine-tuning is all you need to mitigate backdoor attacks
Z Sha, X He, P Berrang, M Humbert, Y Zhang
arXiv preprint arXiv:2212.09067, 2022
142022
From visual prompt learning to zero-shot transfer: Mapping is all you need
Z Yang, Z Sha, M Backes, Y Zhang
arXiv preprint arXiv:2303.05266, 2023
32023
Prompt Stealing Attacks Against Large Language Models
Z Sha, Y Zhang
arXiv preprint arXiv:2402.12959, 2024
22024
Conversation Reconstruction Attack Against GPT Models
J Chu, Z Sha, M Backes, Y Zhang
arXiv preprint arXiv:2402.02987, 2024
2024
Comprehensive Assessment of Toxicity in ChatGPT
B Zhang, X Shen, WM Si, Z Sha, Z Chen, A Salem, Y Shen, M Backes, ...
arXiv preprint arXiv:2311.14685, 2023
2023
系統目前無法執行作業，請稍後再試。
文章 1–7