Prati
Hai Huang
Hai Huang
CISPA Helmholtz Center for Information Security
Potvrđena adresa e-pošte na cispa.de - Početna stranica
Naslov
Citirano
Citirano
Godina
Data Poisoning Attacks to Deep Learning Based Recommender Systems
H Huang, J Mu, NZ Gong, Q Li, B Liu, M Xu
ISOC Network and Distributed System Security Symposium (NDSS), 2021
952021
Composite Backdoor Attacks Against Large Language Models
H Huang, Z Zhao, M Backes, Y Shen, Y Zhang
Findings of the Association for Computational Linguistics: NAACL 2024, 2024
82024
On the Privacy Risks of Cell-Based NAS Architectures
H Huang, Z Zhang, Y Shen, M Backes, Q Li, Y Zhang
ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022
52022
Prompt Backdoors in Visual Prompt Learning
H Huang, Z Zhao, M Backes, Y Shen, Y Zhang
arXiv preprint arXiv:2310.07632, 2023
2023
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–4