Get started
Author

Zhenhua Liu

Observed name: Liu, Zhenhua
OpenAlex ID: A5129870623
Demystifying the Privacy-Utility Trade-off in LLM Interactions
2026 · Liu, Zhenhua, Xie, Zhanxu, et al. · arXiv (Cornell University)
PDF
Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment
2026 · Pan, Weici, Barron, Xander, et al. · arXiv (Cornell University)
PDF
General Techniques for Reducing Key-Switching Overhead in Privacy-Preserving Two-Party Transformer Inference
2026 · Yang, Wenshao, Liu, Zhenhua, et al. · arXiv (Cornell University)
PDF
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
2026 · Miao Ziqi, Lijun Li, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
PDF
SecretVoice1.0: Non-interactive Secure Transformer Inference
2026 · Wenshao Yang, Zhenhua Liu, et al.
Works count: 5
Citation count:
H-index:
I10-index:
Year
Topic
Type