Skip to content

Home Search Authors Pakistan News Saved

SciRah

SciRah does not host or store research papers. Results come live from free, official scholarly APIs, and every paper links back to its original source.

Data sources

OpenAlex
Semantic Scholar
Crossref
CORE
arXiv
PubMed

Privacy policy Terms of service

Tian-Wei Zhang · SciRah

Researcher profile · Semantic Scholar

Tian-Wei Zhang

Share profile

Tian-Wei Zhang — researcher profile on SciRah

h-index: 48
Works: 374
Citations: 12K

Most-cited papers

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Kun Wang, Guibin Zhang, Zhenhong Zhou, Jia-Hao Wu +79 more
2025arXiv.org141 citations
Semantic Scholar
Safety at Scale: A Comprehensive Survey of Large Model Safety
Xingjun Ma, Yi-Feng Gao, Yi-Xu Wang, Ruo-Fan Wang +40 more
2025Robotics67 citations
Semantic Scholar
What Makes a Good LLM Agent for Real-world Penetration Testing?
Ge-Lei Deng, Yi Liu, Yue-Kang Li, Ruo-Zhao Yang +4 more
2026arXiv.org18 citations
Semantic Scholar
Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
Bo-Heng Li, Renjie Gu, Junjie Wang, Le-Yi Qi +4 more
2025Neural Information Processing Systems16 citations
Semantic Scholar
DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
Lizhuo Luo, Zhuoran Shi, Jiajun Luo, Zhi Wang +3 more
2026arXiv.org14 citations
Semantic Scholar
DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
Bo-Heng Li, Junjie Wang, Yi-Ming Li, Zhi-Yang Hu +6 more
2025IEEE Symposium on Security and Privacy11 citations Open access
Semantic Scholar
MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
Xuan-Ye Zhang, Yong-Sen Zheng, Zhu-Qin Xu, Kai Zhou +4 more
2026arXiv.org10 citations
Semantic Scholar
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Rui-Xiao Lin, Xin-Hao Deng, Qing-Ming Li, Jia-Nan Ma +11 more
2026arXiv.org10 citations
Semantic Scholar
Beyond Similarity: Trustworthy Memory Search for Personal AI Agents
Jiawen Zhang, Ke-Jia Chen, Jiachen Ma, Yangfan Hu +6 more
2026arXiv.org9 citations
Semantic Scholar
SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Pei-Gui Qi, Kun-Sheng Tang, Wenbo Zhou, Wei-Ming Zhang +4 more
2025Conference on Computer and Communications Security9 citations Open access
Semantic Scholar
TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
Kangjie Chen, Muyang Li, Guanlin Li, Shudong Zhang +2 more
2025International Conference on Machine Learning9 citations
Semantic Scholar
A Benchmark for Semantic Sensitive Information in LLMs Outputs
Qingjie Zhang, Han Qiu, Di Wang, Yi-Ming Li +5 more
2025International Conference on Learning Representations8 citations
Semantic Scholar
Inception: Jailbreak the Memory Mechanism of Text-to-Image Generation Systems
Shi-Qian Zhao, Jia-Yang Liu, Yi-Ming Li, Run-Yi Hu +7 more
2025arXiv.org8 citations
Semantic Scholar
Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States
Jian-Shuo Dong, Yiming Liu, Mao-Sen Zhang, Nan Deng +5 more
20267 citations
Semantic Scholar
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
Xin-Wei Zhang, Hang-Cheng Liu, Li Bai, Hao Wang +3 more
2026arXiv.org7 citations
Semantic Scholar
Speculating LLMs' Chinese Training Data Pollution from Their Tokens
Qingjie Zhang, Di Wang, Haoting Qian, Liu Yan +6 more
2025Conference on Empirical Methods in Natural Language Processing7 citations
Semantic Scholar
I2I Backdoor: Backdoor Attacks Against Image-to-Image Tasks
Wen-Bo Jiang, Hong-Wei Li, Jia-Ming He, Rui Zhang +3 more
2025IEEE Transactions on Dependable and Secure Computing7 citations
Semantic Scholar
AuthUp: A Privacy-Preserving V2I Authentication Scheme for Vehicular Ad Hoc Networks
Xincheng Li, Xinchun Yin, Jian-Ting Ning, Tian-Wei Zhang
2025IEEE Transactions on Vehicular Technology7 citations
Semantic Scholar
State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Pengcheng Li, Jie Zhang, Tian-Wei Zhang, Han Qiu +4 more
2026arXiv.org6 citations
Semantic Scholar
Physical Prompt Injection Attacks on Large Vision-Language Models
Chen Ling, Kai Hu, Hang-Cheng Liu, Xing-Shuo Han +2 more
2026arXiv.org6 citations
Semantic Scholar
Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
Meng Chen, Kun Wang, Li Lu, Jia-Heng Zhang +1 more
2026IEEE Symposium on Security and Privacy5 citations
Semantic Scholar
FaceID-6M: A Large-Scale, Open-Source FaceID Customization Dataset
Shuhe Wang, Xiaoya Li, Jiwei Li, Guo-Yin Wang +7 more
2025arXiv.org5 citations
Semantic Scholar
BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
Xiaobei Yan, Yi-Ming Li, Zhao-Xin Fan, Han Qiu +1 more
2025arXiv.org5 citations
Semantic Scholar
Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
Xiang-Lin Yang, Bryan Hooi, Ge-Lei Deng, Tian-Wei Zhang +1 more
2026arXiv.org4 citations
Semantic Scholar
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
Ye-Chao Zhang, Shi-Qian Zhao, Jia-Wen Zhang, Jie Zhang +4 more
2026arXiv.org4 citations
Semantic Scholar
Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution
Ye-Chao Zhang, Shi-Qian Zhao, Jie Zhang, Ge-Lei Deng +4 more
2026arXiv.org4 citations
Semantic Scholar
SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
Renyang Liu, Kangjie Chen, Han Qiu, Jie Zhang +3 more
2026arXiv.org4 citations
Semantic Scholar
Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
Yanghao Su, Wenbo Zhou, Tian-Wei Zhang, Qi Han +3 more
2026arXiv.org4 citations
Semantic Scholar
PrivTF: Efficient and Privacy-Preserving Transformer Inference With Optimized Protocols for Secure NLP
Zi-Wei Peng, Kaiping Xue, Bin Zhu, Ya-Xuan Huang +3 more
2026IEEE Transactions on Network Science and Engineering4 citations
Semantic Scholar
Automated Red Teaming for Text-to-Image Models Through Feedback-Guided Prompt Iteration with Vision-Language Models
Wei Xu, Kangjie Chen, Jiawei Qiu, Yu-Yang Zhang +4 more
2025IEEE International Conference on Computer Vision4 citations
Semantic Scholar
SightCVC: An Efficient and Compatible Multi-Chain Transaction Protocol in Heterogeneous Blockchain Systems
Haonan Yang, Tian-Wei Zhang, Zuo-Bing Ying, Runjie Yang +1 more
2025IEEE Transactions on Information Forensics and Security4 citations
Semantic Scholar
DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
Hao-Ran Ou, Kangjie Chen, Ge-Lei Deng, Hang-Cheng Liu +3 more
2026arXiv.org3 citations
Semantic Scholar
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
Zihao Wang, Yi-Ming Li, Yu-Tong Wu, Zhe-Yu Liu +7 more
2026arXiv.org3 citations
Semantic Scholar
Inference-time Alignment via Sparse Junction Steering
Run-Yi Hu, Jie Zhang, Shi-Qian Zhao, Jiale Meng +6 more
2026arXiv.org3 citations
Semantic Scholar
Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models
Shi-Qian Zhao, Chong-Wen Wang, Yiming Li, Yihao Huang +6 more
2025Network and Distributed System Security Symposium3 citations
Semantic Scholar
Mission: Impossible - Image-Based Geolocation with Large Vision Language Models
Yi Liu, Ge-Lei Deng, Junchen Ding, Yuekang Li +4 more
2025Proceedings on Privacy Enhancing Technologies3 citations Open access
Semantic Scholar
Efficient Fuzzy Private Set Intersection from Secret-Shared OPRF
Xinpeng Yang, Meng Hao, Chenkai Weng, Robert H. Deng +2 more
2026IEEE Symposium on Security and Privacy2 citations
Semantic Scholar
GoSSamer: Lightweight and Linear-Communication Asynchronous (Dynamic Proactive) Secret Sharing and the Applications
Xin-Xin Xing, Yi-Zhong Liu, Boyang Liao, Jianwei Liu +4 more
2026IEEE Symposium on Security and Privacy2 citations
Semantic Scholar
Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models
Xin-Wei Zhang, Li Bai, Tian-Wei Zhang, You-Chen Zhang +4 more
20262 citations
Semantic Scholar
Detecting Perception-Based Attacks using Visual Odometry: Inconsistency Modeling and Checking on Robotic States
Yuan Xu, Ge-Lei Deng, Tian-Wei Zhang
2025IEEE International Conference on Robotics and Automation2 citations
Semantic Scholar
BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
Zi-Han Wang, Hong-Wei Li, Rui Zhang, Wen-Bo Jiang +4 more
2025arXiv.org2 citations
Semantic Scholar
Clean Image May Be Dangerous: Data Poisoning Attacks Against Deep Hashing
Shuai Li, Jie Zhang, Yuang Qi, Kejiang Chen +3 more
2025IEEE transactions on multimedia2 citations Open access
Semantic Scholar
The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges
Mao-Sen Zhang, Jian-Shuo Dong, Bo-Han Lu, Wen-Yue Li +4 more
20261 citations
Semantic Scholar
AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications
Ruo-Zhao Yang, Ming-Fei Cheng, Ge-Lei Deng, Jun-Jie Wang +2 more
2026arXiv.org1 citations
Semantic Scholar
Sanitizer: Blazing-Fast, Private, and Robust Federated Learning
Hanxiao Chen, Hong-Wei Li, Meng Hao, Jia Hu +4 more
2026IEEE Transactions on Information Forensics and Security1 citations
Semantic Scholar
ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems
Shu-Yu Jiang, Yue Ran, Kaiyu Xu, Xing-Shu Chen +4 more
20261 citations
Semantic Scholar
δ-SCALPEL: Docker Image Slimming Based on Source Code Static Analysis
Jiaxuan Han, Cheng Huang, Jiayong Liu, Tian-Wei Zhang
2026IEEE Transactions on Software Engineering1 citations
Semantic Scholar
An Advanced Gradient Leakage Attack Against Duplicate Labels via Model Outputs Reconstruction
Kunlan Xiang, Hao-Miao Yang, Meng Hao, Zikang Ding +3 more
2026IEEE Transactions on Dependable and Secure Computing1 citations
Semantic Scholar
Ownership Verification of Your NLG Models With Semantic Combination Watermarks
Chunlong Xie, Tao Xiang, Shang-Wei Guo, Biwen Chen +3 more
2026IEEE Transactions on Dependable and Secure Computing1 citations
Semantic Scholar
Discovering Safety Violations of Decision-Making in Autonomous Driving Systems from Accident-Free Traffic Scenarios
Hao-Xiang Tian, Yuan Zhou, An Guo, Guo-Quan Wu +5 more
2026ACM Transactions on Software Engineering and Methodology1 citations Open access
Semantic Scholar

Frequent co-authors

Invite them to SciRah by sharing their profile.

Shi-Qian Zhao×6
Invite
Shi-Qian Zhao — researcher profile on SciRah
Han Qiu×6
Invite
Han Qiu — researcher profile on SciRah
Kangjie Chen×6
Invite
Kangjie Chen — researcher profile on SciRah
Ge-Lei Deng×6
Invite
Ge-Lei Deng — researcher profile on SciRah

×5

Invite

Yi-Ming Li — researcher profile on SciRah

Invite

Jie Zhang — researcher profile on SciRah

Ye-Chao Zhang×4

Invite

Ye-Chao Zhang — researcher profile on SciRah

Invite

Neng-Hai Yu — researcher profile on SciRah

Invite

Hong-Wei Li — researcher profile on SciRah

Jian-Shuo Dong×3

Invite

Jian-Shuo Dong — researcher profile on SciRah

Invite

Han Qiu — researcher profile on SciRah

Invite

Wenbo Zhou — researcher profile on SciRah