Get started
Author

Zihan Wang

Observed name: Wang, Zihan
ORCID: 0000-0002-6536-2948
Observed ORCID: 0000-0002-6536-2948
OpenAlex ID: A5091939001
Data Hiding With Deep Learning: A Survey Unifying Digital Watermarking and Steganography
2023 · Zihan Wang, Olivia Byrnes, et al. · IEEE Transactions on Computational Social Systems · 136
PDF
BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation
2024 · Liyang Liu, Zihan Wang, et al. · IEEE Winter Conference on Applications of Computer Vision · 35
PDF
CORELOCKER: Neuron-level Usage Control
2024 · Zihan Wang, Zhongkui Ma, et al. · IEEE Symposium on Security and Privacy (S&P) · 12
Uncovering Gradient Inversion Risks in Practical Language Model Training
2024 · Xinguo Feng, Zhongkui Ma, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 7
PDF
M^4I: Multi-Modal Models Membership Inference
2022 · Pingyi Hu, Zihan Wang, et al. · neural information processing systems · 4
PDF
AI Model Modulation with Logits Redistribution
2025 · Zihan Wang, Zhongkui Ma, et al. · International World Wide Web Conference (WWW) · 3
PDF
Formalizing Robustness Against Character-Level Perturbations for Neural Network Language Models
2023 · Zhongkui Ma, Xinguo Feng, et al. · Lecture notes in computer science · 3
Convex Hull Approximation for Activation Functions
2025 · Zhongkui Ma, Zihan Wang, et al. · Proceedings of the ACM on Programming Languages · 2
PDF
Re-Key-Free, Risky-Free: Adaptable Model Usage Control
2026 · Zihan Wang, Zhongkui Ma, et al. · IEEE European Symposium on Security and Privacy · 1
Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation
2026 · Xinguo Feng, Zhongkui Ma, et al. · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · 1
ExactUMM: Exact Task and Data Unlearning via Model Merging
2026 · Shogo Terashima, Priyanka Singh, et al.
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
2026 · Chi Wang, Hanwen Wang, et al. · Lecture notes in computer science
The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts
2026 · Yu, Manjiang, Li, Hongji, et al. · arXiv (Cornell University)
PDF
Shadow Queries for Private Retrieval in Vector Databases
2026 · Feng, Xinguo, Ma, Zhongkui, et al. · arXiv (Cornell University)
PDF
Embedded Graph Flows for Categorical Graph Generation
2026 · Ma, Ethan, Wang, Zihan, et al. · arXiv (Cornell University)
PDF
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
2026 · Wang, Chi, Wang, Hanwen, et al. · arXiv (Cornell University)
PDF
Beyond the Scope: Security Testing of Permission Management in Team Workspaces
2026 · Liuhuo Wan, Chuan Yan, et al. · IEEE Transactions on Dependable and Secure Computing
AI usage control
2026 · Zihan Wang
Leveraging Robustness-Aware Channel Activation for Privacy Protection and Tracing Forensics
2026 · Haodi Wang, Zihan Wang, et al. · IEEE Transactions on Dependable and Secure Computing
Variational Feature Compression for Model-Specific Representations
2026 · Guo, Zinan, Wang, Zihan, et al. · arXiv (Cornell University)
PDF
AI Model Modulation with Logits Redistribution
2026 · Wang, Zihan, Ma, Zhongkui, et al. · arXiv (Cornell University)
PDF
Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation
2026 · Feng, Xinguo, Ma, Zhongkui, et al. · arXiv (Cornell University)
PDF
Re-Key-Free, Risky-Free: Adaptable Model Usage Control
2025 · Wang, Zihan, Ma, Zhongkui, et al. · arXiv (Cornell University)
PDF
Works count: 24
Citation count: 204
H-index: 4
I10-index: 3
Year
Topic
Type