Seguir
Yupei Liu
Yupei Liu
Duke University
Dirección de correo verificada de duke.edu - Página principal
Título
Citado por
Citado por
Año
Badencoder: Backdoor Attacks to Pre-Trained Encoders in Self-Supervised Learning
J Jia, Y Liu, NZ Gong
2022 IEEE Symposium on Security and Privacy (SP), 2043-2059, 2022
1962022
Formalizing and Benchmarking Prompt Injection Attacks and Defenses
Y Liu, Y Jia, R Geng, J Jia, NZ Gong
USENIX Security Symposium, 1831-1847, 2024
99*2024
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks
J Jia, Y Liu, X Cao, NZ Gong
Proceedings of the AAAI Conference on Artificial Intelligence 36 (9), 9575-9583, 2022
842022
Security Analysis of {Camera-LiDAR} Fusion against {Black-Box} Attacks on Autonomous Vehicles
RS Hallyburton, Y Liu, Y Cao, ZM Mao, M Pajic
USENIX Security Symposium, 1903-1920, 2022
812022
StolenEncoder: Stealing Pre-Trained Encoders in Self-Supervised Learning
Y Liu, J Jia, H Liu, NZ Gong
ACM Conference on Computer and Communications Security (CCS), 2115-2128, 2022
502022
{PORE}: Provably Robust Recommender Systems against Data Poisoning Attacks
J Jia, Y Liu, Y Hu, NZ Gong
USENIX Security Symposium, 1703-1720, 2023
132023
TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning
Y Liu, Y Wang, J Jia
Proceedings of the AAAI Conference on Artificial Intelligence, 2025
2025
Evaluating LLM-based Personal Information Extraction and Countermeasures
Y Liu, Y Jia, J Jia, NZ Gong
USENIX Security Symposium, 2025
2025
Defending Deep Regression Models against Backdoor Attacks
L Du, Y Liu, J Jia, G Lan
arXiv preprint arXiv:2411.04811, 2024
2024
FMLock: Preventing Unauthorized Use of Large Foundation Models
Y Liu, J Jia, NZ Gong
2023
DRMGuard: Defending Deep Regression Models against Backdoor Attacks
L Du, Y Liu, J Jia, G Lan
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–11