Hongbin Liu - RankMe

34 papers A* 10Journal 20Unranked 4

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment. AISec@CCS Zedian Shao, Hongbin Liu, Jaden Mu, Neil Gong
2025	J	`jnl`	Periodic Recovery From Poisoning Attacks in Machine Learning. IEEE Trans. Dependable Secur. Comput. Yuepeng Hu, Minghong Fang, Yuqi Jia, Hongbin Liu, Neil Zhenqiang Gong
2024	A*	`conf`	AudioMarkBench: Benchmarking Robustness of Audio Watermarking. NeurIPS Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang, Neil Gong
2024	J	`jnl`	AudioMarkBench: Benchmarking Robustness of Audio Watermarking. CoRR Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang, Neil Zhenqiang Gong
2024	J	`jnl`	Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models. CoRR Zhongye Liu, Hongbin Liu, Yuepeng Hu, Zedian Shao, Neil Zhenqiang Gong
2024	A*	`conf`	Data Poisoning Based Backdoor Attacks to Contrastive Learning. CVPR Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
2024	J	`jnl`	Making LLMs Vulnerable to Prompt Injection via Poisoning Alignment. CoRR Zedian Shao, Hongbin Liu, Jaden Mu, Neil Zhenqiang Gong
2024	A*	`conf`	Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models. USENIX Security Symposium Hongbin Liu, Michael K. Reiter, Neil Zhenqiang Gong
2024	J	`jnl`	Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models. CoRR Hongbin Liu, Michael K. Reiter, Neil Zhenqiang Gong
2024	—	`conf`	Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning. SP (Workshops) Hongbin Liu, Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong
2024	J	`jnl`	Refusing Safe Prompts for Multi-modal Large Language Models. CoRR Zedian Shao, Hongbin Liu, Yuepeng Hu, Neil Zhenqiang Gong
2024	J	`jnl`	Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning. CoRR Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Zhenqiang Gong
2024	—	`conf`	Visual Hallucinations of Multi-modal Large Language Models. ACL (Findings) Wen Huang, Hongbin Liu, Minxin Guo, Neil Gong
2024	J	`jnl`	Visual Hallucinations of Multi-modal Large Language Models. CoRR Wen Huang, Hongbin Liu, Minxin Guo, Neil Zhenqiang Gong
2023	J	`jnl`	Generation-based fuzzing? Don't build a new generator, reuse! Comput. Secur. Chengbin Pang, Hongbin Liu, Yifan Wang, Neil Zhenqiang Gong, Bing Mao, Jun Xu
2023	A*	`conf`	PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees. CVPR Jinghuai Zhang, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
2023	J	`jnl`	PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees. CoRR Jinghuai Zhang, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
2022	A*	`conf`	Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations. ICLR Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong
2022	J	`jnl`	CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning. CoRR Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
2022	A*	`conf`	PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning. USENIX Security Symposium Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
2022	J	`jnl`	PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning. CoRR Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
2022	J	`jnl`	Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning. CoRR Hongbin Liu, Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong
2022	—	`conf`	Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning. ECCV (31) Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang
2022	J	`jnl`	Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning. CoRR Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang
2022	A*	`conf`	StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning. CCS Yupei Liu, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
2022	J	`jnl`	StolenEncoder: Stealing Pre-trained Encoders. CoRR Yupei Liu, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
2021	J	`jnl`	10 Security and Privacy Problems in Self-Supervised Learning. CoRR Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
2021	A*	`conf`	EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning. CCS Hongbin Liu, Jinyuan Jia, Wenjie Qu, Neil Zhenqiang Gong
2021	J	`jnl`	EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning. CoRR Hongbin Liu, Jinyuan Jia, Wenjie Qu, Neil Zhenqiang Gong
2021	A*	`conf`	On the Intrinsic Differential Privacy of Bagging. IJCAI Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
2021	A*	`conf`	PointGuard: Provably Robust 3D Point Cloud Classification. CVPR Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
2021	J	`jnl`	PointGuard: Provably Robust 3D Point Cloud Classification. CoRR Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
2020	J	`jnl`	Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations. CoRR Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong
2020	J	`jnl`	On the Intrinsic Differential Privacy of Bagging. CoRR Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong