Sledovat
Xinlei He
Xinlei He
Assistant Professor, HKUST(GZ)
E-mailová adresa ověřena na: hkust-gz.edu.cn - Domovská stránka
Název
Citace
Citace
Rok
Stealing Links from Graph Neural Networks
X He, J Jia, M Backes, NZ Gong, Y Zhang
USENIX Security Symposium, 2021
1992021
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
Y Liu, R Wen, X He, A Salem, Z Zhang, M Backes, E De Cristofaro, M Fritz, ...
USENIX Security Symposium, 2021
1622021
Node-level membership inference attacks against graph neural networks
X He, R Wen, Y Wu, M Backes, Y Shen, Y Zhang
arXiv preprint arXiv:2102.05429, 2021
1252021
MGTBench: Benchmarking Machine-generated Text Detection
X He, X Shen, Z Chen, M Backes, Y Zhang
ACM SIGSAC Conference on Computer and Communications Security (CCS), 2024
1142024
Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models
Y Qu, X Shen, X He, M Backes, S Zannettou, Y Zhang
Proceedings of the 2023 ACM SIGSAC conference on computer and communications …, 2023
1122023
Model Stealing Attacks Against Inductive Graph Neural Networks
Y Shen, X He, Y Han, Y Zhang
IEEE Symposium on Security and Privacy, 2021
952021
DeepScan: Exploiting deep learning for malicious account detection in location-based social networks
Q Gong, Y Chen, X He, Z Zhuang, T Wang, H Huang, X Wang, X Fu
IEEE Communications Magazine 56 (11), 21-27, 2018
932018
Jailbreak attacks and defenses against large language models: A survey
S Yi, Y Liu, Z Sun, T Cong, X He, J Song, K Xu, Q Li
arXiv preprint arXiv:2407.04295, 2024
642024
SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders
T Cong, X He, Y Zhang
ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022
632022
Data poisoning attacks against multimodal encoders
Z Yang, X He, Z Li, M Backes, M Humbert, P Berrang, Y Zhang
International Conference on Machine Learning, 39299-39313, 2023
582023
Quantifying and Mitigating Privacy Risks of Contrastive Learning
X He, Y Zhang
ACM SIGSAC Conference on Computer and Communications Security (CCS), 2021
572021
You only prompt once: On the capabilities of prompt learning on large language models to tackle toxic content
X He, S Zannettou, Y Shen, Y Zhang
IEEE Symposium on Security and Privacy, 2023
452023
DatingSec: Detecting malicious accounts in dating apps using a content-based attention network
X He, Q Gong, Y Chen, Y Zhang, X Wang, X Fu
IEEE Transactions on Dependable and Secure Computing 18 (5), 2193-2208, 2021
452021
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
412022
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
362022
Auditing Membership Leakages of Multi-Exit Networks
Z Li, Y Liu, X He, N Yu, M Backes, Y Zhang
ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022
362022
On the evolution of (hateful) memes by means of multimodal contrastive learning
Y Qu, X He, S Pierson, M Backes, Y Zhang, S Zannettou
2023 IEEE Symposium on Security and Privacy (SP), 293-310, 2023
302023
Membership-doctor: Comprehensive assessment of membership inference against machine learning models
X He, Z Li, W Xu, C Cornelius, Y Zhang
arXiv preprint arXiv:2208.10445, 2022
282022
Cross-site prediction on social influence for cold-start users in online social networks
Q Gong, Y Chen, X He, Y Xiao, P Hui, X Wang, X Fu
ACM Transactions on the Web (TWEB) 15 (2), 1-23, 2021
252021
Generative watermarking against unauthorized subject-driven image synthesis
Y Ma, Z Zhao, X He, Z Li, M Backes, Y Zhang
arXiv preprint arXiv:2306.07754, 2023
222023
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–20