Tianwei Zhang

University of Electronic Science and Technology of China — China

Computer Science · Physical Sciences

15h-index925citations50works1.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Security and Verification in Computing(22), Advanced Malware Detection Techniques(18), Cloud Data Security Solutions(10), Cryptographic Implementations and Security(7), Topic Modeling(6)

Publications50 total

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
ArXiv.org·2025Open Access
Predicting Biochemical Recurrence After Robot-Assisted Prostatectomy with Interpretable Machine Learning Model
Journal of Clinical Medicine·2025Open Access
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
arXiv (Cornell University)·2025Open Access
When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
arXiv (Cornell University)·2025Open Access
Coward: Collision-based Watermark for Proactive Federated Backdoor Detection
arXiv (Cornell University)·2025Open Access
DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
arXiv (Cornell University)·2025Open Access
IRCopilot: Automated Incident Response with Large Language Models
arXiv (Cornell University)·2025Open Access
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
2025· 2 cited
When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
arXiv (Cornell University)·2025Open Access
Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
arXiv (Cornell University)·2025Open Access
Enhancing source-free domain adaptation in Medical Image Segmentation via regulated model self-training
Medical Image Analysis·2025· 4 cited
SSD: A State-based Stealthy Backdoor Attack For Navigation System in UAV Route Planning
arXiv (Cornell University)·2025Open Access
CipherGuard: Compiler-aided Mitigation against Ciphertext Side-channel Attacks
arXiv (Cornell University)·2025Open Access
An Effective Docker Image Slimming Approach Based on Source Code Data Dependency Analysis
arXiv (Cornell University)·2025Open Access
SuperMark: Robust and Training-free Image Watermarking via\n Diffusion-based Super-Resolution
arXiv (Cornell University)·2024· 1 citedOpen Access
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
arXiv (Cornell University)·2024Open Access
UniGuard: A Unified Hardware-oriented Threat Detector for FPGA-based AI Accelerators
2024· 1 cited
Protecting Confidential Virtual Machines from Hardware Performance Counter Side Channels
2024· 3 cited
BadEdit: Backdooring large language models by model editing
arXiv (Cornell University)·2024· 7 citedOpen Access
PRIME: Protect Your Videos From Malicious Editing
arXiv (Cornell University)·2024Open Access
page 1 of 3Next →

Frequent Co-authors

Ruby B. Lee(15), Yinqian Zhang(8), Gelei Deng(5), Han Qiu(5), Jakub Szefer(4), Kangjie Chen(4), Boheng Li(4), Yiming Li(4), Jie Zhang(4), Xiaoxuan Lou(3), Jun Jiang(3), Run Wang(3), Yuekang Li(2), Jiwei Li(2), Junbo Gong(2), Shangwei Guo(2), Yanhao Wei(2), Yankai Fu(2), Zhenting Wang(2), Runyi Hu(2)