Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Bin Liu

Bin Liu

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

Crypto×4Vision×3AI×1ML×1

Frequent co-authors

Hongbin Liu2×
Neil Zhenqiang Gong2×
Yi Yang1×
Jinyang Huang1×
Binbin Liu1×
Feng-Qi Cui1×

Research Timeline

2026
Hidden Elo: Private Matchmaking through Encrypted Rating Systems

The paper proposes H-Elo, a Fully Homomorphic Encryption (FHE)-based system that enables private and secure matchmaking by keeping user rating values encrypted during the traditional rating update process.

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensitive information from them.

Robustness of Vision Foundation Models to Common Perturbations

This paper systematically studies the robustness of vision foundation models to common image perturbations, finding that most models are generally non-robust and proposing a fine-tuning method to improve this resilience.

Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget

The paper introduces Checkerboard, a novel, learning-free clean-label backdoor attack that efficiently poisons training data to compromise model integrity with minimal poisoning budget.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.CVRecentMay 2, 2026

Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget

Yi Yang, Jinyang Huang, Binbin Liu, Feng-Qi Cui +4 more

The paper introduces Checkerboard, a novel, learning-free clean-label backdoor attack that efficiently poisons training data to compromise model integrity with minimal poisoning budget.

View →
cs.CRcs.CVRecentApr 16, 2026

Robustness of Vision Foundation Models to Common Perturbations

Hongbin Liu, Zhengyuan Jiang, Cheng Hong, Neil Zhenqiang Gong

This paper systematically studies the robustness of vision foundation models to common image perturbations, finding that most models are generally non-robust and proposing a fine-tuning method to impr…

View →
cs.CVcs.AIcs.CRRecentApr 10, 2026

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection

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

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

View →
cs.CRRecentMar 27, 2026

Hidden Elo: Private Matchmaking through Encrypted Rating Systems

Mindaugas Budzys, Bin Liu, Antonis Michalas

The paper proposes H-Elo, a Fully Homomorphic Encryption (FHE)-based system that enables private and secure matchmaking by keeping user rating values encrypted during the traditional rating update pro…

View →