Get started
Author

Zihao Wang

Prompt Injection attack against LLM-integrated Applications
2023 · Liu, Yi, Deng, Gelei, et al. · arXiv (Cornell University) · 100
PDF
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
2024 · Xiaoyi Chen, Siyuan Tang, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 35
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
2024 · Mengxin Zheng, Jiaqi Xue, et al. · Lecture notes in computer science · 15
PDF
Zero in and TimeFuzz: Detection and Mitigation of Cache Side-Channel Attacks
2019 · ZiHao Wang, ShuangHe Peng, et al. · Lecture notes in computer science · 9
The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems
2025 · Linke Song, Zixuan Pang, et al. · IEEE Transactions on Information Forensics and Security · 7
PDF
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
2024 · Rui Zhu, Di Tang, et al. · Network and Distributed System Security Symposium · 6
PDF
Defeating Hardware Prefetchers in Flush+Reload Side-Channel Attack
2021 · Zihao Wang, Shuanghe Peng, et al. · IEEE Access · 5
PDF
Alexa, is the skill always safe? Uncover Lenient Skill Vetting Process and Protect User Privacy at Run Time
2024 · Tu Le, Dongfang Zhao, et al. · IEEE/ACM International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS) · 4
DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
2024 · Wang, Zihao, Zhu, Rui, et al. · arXiv (Cornell University) · 4
PDF
The Danger of Minimum Exposures: Understanding Cross-App Information Leaks on iOS through Multi-Side-Channel Learning
2023 · Zihao Wang, Jiale Guan, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 4
PDF
Rigging the Foundation: Manipulating Pre-training for Advanced Membership Inference Attacks
2025 · Zihao Wang, Rui Zhu, et al. · IEEE Symposium on Security and Privacy (S&P) · 3
EvilHarmony: Stealthy Adversarial Attacks Against Black-Box Speech Recognition Systems
2025 · Xuejing Yuan, Jiangshan Zhang, et al. · IEEE Symposium on Security and Privacy (S&P) · 2
CryptPEFT: Efficient and Private Neural Network Inference via Parameter-Efficient Fine-Tuning
2026 · Saisai Xia, Wenhao Wang, et al. · Network and Distributed System Security Symposium · 1
PDF
Hey, That’s My Data! Token-Only Dataset Inference in Large Language Models
2026 · Chen Xiong, Zihao Wang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 1
PDF
Large Language Models’ Simulation of Patient Comprehension of Discharge Summaries: Multimodel Evaluation Study
2026 · Xinyao Ma, Rui Zhu, et al. · Journal of Medical Internet Research
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
2026 · Wang, Zihao, Li, Yiming, et al. · arXiv (Cornell University)
PDF
Activation-Guided Local Editing for Jailbreaking Attacks
2026 · Association for Computational Linguistics 2026, Du, Haohua, et al. · Underline Science Inc.
AudioStealer: Extracting Audio Prompts via Shapley Value-Guided Query Search
2026 · Association for Computational Linguistics 2026, Du, Xingjian, et al. · Underline Science Inc.
Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
2026 · Association for Computational Linguistics 2026, Chen, Pin-Yu, et al. · Underline Science Inc.
Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents
2026 · Xu, Zhen, Wang, Zihao, et al. · arXiv (Cornell University)
PDF
DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
2026 · Sha, Haichao, Wang, Zihao, et al. · arXiv (Cornell University)
PDF
Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
2026 · Fei, Zekun, Wang, Zihao, et al. · arXiv (Cornell University)
PDF
LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
2026 · Gong, Yuyang, Wang, Zihao, et al. · arXiv (Cornell University)
PDF
RPGen: Robust and Differentially Private Synthetic Image Generation
2026 · Zihao Wang, Hao Peng, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
Trojans in Artificial Intelligence (TrojAI) Final Report
2026 · Reese, Kristopher W., Kulp-McDowall, Taylor, et al. · arXiv (Cornell University)
PDF
Works count: 35
Citation count: 197
H-index: 6
I10-index: 3
Year
Topic
Type