Hongbin Liu

According to our database, Hongbin Liu authored at least 21 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Making LLMs Vulnerable to Prompt Injection via Poisoning Alignment.

Zedian Shao, Hongbin Liu, Jaden Mu, Neil Zhenqiang Gong

CoRR, 2024

Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models.

Zhongye Liu, Hongbin Liu, Yuepeng Hu, Zedian Shao, Neil Zhenqiang Gong

CoRR, 2024

Refusing Safe Prompts for Multi-modal Large Language Models.

Zedian Shao, Hongbin Liu, Yuepeng Hu, Neil Zhenqiang Gong

CoRR, 2024

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning.

Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Zhenqiang Gong

CoRR, 2024

AudioMarkBench: Benchmarking Robustness of Audio Watermarking.

Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang, Neil Zhenqiang Gong

CoRR, 2024

Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models.

Hongbin Liu, Michael K. Reiter, Neil Zhenqiang Gong

Proceedings of the 33rd USENIX Security Symposium, 2024

Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning.

Hongbin Liu, Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong

Proceedings of the IEEE Security and Privacy, 2024

Data Poisoning Based Backdoor Attacks to Contrastive Learning.

Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Visual Hallucinations of Multi-modal Large Language Models.

Wen Huang, Hongbin Liu, Minxin Guo, Neil Gong

Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023

Generation-based fuzzing? Don't build a new generator, reuse!

Chengbin Pang, Hongbin Liu, Yifan Wang, Neil Zhenqiang Gong, Bing Mao, Jun Xu

Comput. Secur., June, 2023

PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees.

Jinghuai Zhang, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning.

Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

CoRR, 2022

StolenEncoder: Stealing Pre-trained Encoders.

Yupei Liu, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

CoRR, 2022

PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning.

Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

Proceedings of the 31st USENIX Security Symposium, 2022

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations.

Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong

Proceedings of the Tenth International Conference on Learning Representations, 2022

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning.

Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang

Proceedings of the Computer Vision - ECCV 2022, 2022

StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning.

Yupei Liu, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022

2021

10 Security and Privacy Problems in Self-Supervised Learning.

Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

CoRR, 2021

On the Intrinsic Differential Privacy of Bagging.

Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

PointGuard: Provably Robust 3D Point Cloud Classification.

Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning.

Hongbin Liu, Jinyuan Jia, Wenjie Qu, Neil Zhenqiang Gong

Proceedings of the CCS '21: 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, Republic of Korea, November 15, 2021