Get started
Author

Yinzhi Cao

Observed name: Cao, Yinzhi
Observed institution: Johns Hopkins University
OpenAlex ID: A5139790247
Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis
2026 · Penghui Li, Hong Yau Chong, et al. · IEEE Symposium on Security and Privacy (S&P) · 1
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
2026 · Yang, Rui, Xu, Junjie, et al. · arXiv (Cornell University)
PDF
Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services
2026 · Sun, Bowen, Zhao, Zhengyue, et al. · arXiv (Cornell University)
PDF
KeyPooling: Measuring Where LLM API Relay Paths Collapse Prompt Cache Isolation
2026 · Sun, Bowen, Cai, Yixi, et al. · arXiv (Cornell University)
PDF
Mystra: Declarative Dynamic Taint Analysis via Shadow Virtual Machine
2026 · Zhang, Zhuohao, Liu, Junkun, et al. · arXiv (Cornell University)
PDF
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
2026 · Association for Computational Linguistics 2026, Cao, Yinzhi, et al. · Underline Science Inc.
Practical Covert Channel Across Isolated Browser Instances via GPU Command Queue Contention
2026 · Jinhong Liu, Zifeng Kang, et al. · IEEE Symposium on Security and Privacy (S&P)
The First Large-Scale Systematic Study of Python Class Pollution Vulnerability
2026 · Zhengyu Liu, Jiacheng Zhong, et al. · IEEE Symposium on Security and Privacy (S&P)
Poisoned by the Host: Large-Scale Measurement of Host Name Poisoning in Web Applications
2026 · Rui Yang, Haoyu Wang, et al. · IEEE Symposium on Security and Privacy (S&P)
Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis
2026 · Li, Penghui, Chong, Hong Yau, et al. · arXiv (Cornell University)
PDF
SwitchNet: protecting neural networks by structure obfuscation and switch-controlled inference
2026 · Yuling Cai, Guozhu Meng, et al. · Cybersecurity
PDF
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
2026 · Li, Qi, Wang, Cheng-Long, et al. · arXiv (Cornell University)
PDF
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
2026 · Qi Li, Cheng-Long Wang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Your Cursor is Not Secure: Command Line Interface Agent Can Expose Realistic Risks Through Tactics, Techniques, and Procedures
2026 · Luo, Weidi, Zhang, Qiming, et al. · Rare & Special e-Zone (The Hong Kong University of Science and Technology)
AdaProb: Efficient Machine Unlearning via Adaptive Probability
2024 · Zhao, Zihao, Yang, Yuchen, et al. · arXiv (Cornell University)
PDF
Works count: 15
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type