Hongbin Liu

Publication Activity (10 Years)

Years Active: 2022-2024
Publications (10 Years): 18

Top Topics

Labeled Examples

Supervised Learning

Top Venues

USENIX Security Symposium

Publications

Hongbin Liu, Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning. SP (Workshops) (2024)
Hongbin Liu, Michael K. Reiter, Neil Zhenqiang Gong
Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models. USENIX Security Symposium (2024)
Zedian Shao, Hongbin Liu, Yuepeng Hu, Neil Zhenqiang Gong
Refusing Safe Prompts for Multi-modal Large Language Models. CoRR (2024)
Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang, Neil Zhenqiang Gong
AudioMarkBench: Benchmarking Robustness of Audio Watermarking. CoRR (2024)
Hongbin Liu, Michael K. Reiter, Neil Zhenqiang Gong
Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models. CoRR (2024)
Wen Huang, Hongbin Liu, Minxin Guo, Neil Zhenqiang Gong
Visual Hallucinations of Multi-modal Large Language Models. CoRR (2024)
Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Zhenqiang Gong
Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning. CoRR (2024)
Wen Huang, Hongbin Liu, Minxin Guo, Neil Gong
Visual Hallucinations of Multi-modal Large Language Models. ACL (Findings) (2024)
Jinghuai Zhang, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees. CVPR (2023)
Jinghuai Zhang, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees. CoRR (2023)
Hongbin Liu, Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning. CoRR (2022)
Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning. CoRR (2022)
Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning. CoRR (2022)
Yupei Liu, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning. CCS (2022)
Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang
Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning. CoRR (2022)
Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong
Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations. ICLR (2022)
Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang
Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning. ECCV (31) (2022)
Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning. USENIX Security Symposium (2022)