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

Yi Liu · SciRah

Researcher profile · Semantic Scholar

Yi Liu

Share profile

Yi Liu — researcher profile on SciRah

h-index: 15
Works: 45
Citations: 1,187

Most-cited papers

PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing
Ge-Lei Deng, Yi Liu, V. Vilches, Peng Liu +6 more
2024USENIX Security Symposium359 citations
Semantic Scholar
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
Zi-Hao Xu, Yi Liu, Ge-Lei Deng, Yuekang Li +1 more
2024Annual Meeting of the Association for Computational Linguistics157 citations Open access
Semantic Scholar
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Yi Liu, Wei-Zhe Wang, Rui Feng, Yao Zhang +4 more
2026arXiv.org121 citations
Semantic Scholar
A Hitchhiker’s Guide to Jailbreaking ChatGPT via Prompt Engineering
Yi Liu, Ge-Lei Deng, Zheng-Zi Xu, Yuekang Li +5 more
2024SEA4DQ@SIGSOFT FSE105 citations
Semantic Scholar
LLM Jailbreak Attack versus Defense Techniques - A Comprehensive Study
Zi-Hao Xu, Yi Liu, Ge-Lei Deng, Yuekang Li +1 more
2024arXiv.org81 citations
Semantic Scholar
"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
Yi Liu, Zhi-Hao Chen, Yan-Jun Zhang, Ge-Lei Deng +3 more
202653 citations
Semantic Scholar
Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
Yubin Qu, Yi Liu, Tong-Cheng Geng, Ge-Lei Deng +4 more
2026arXiv.org48 citations
Semantic Scholar
Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models
Ning-Ke Li, Yuekang Li, Yi Liu, Ling Shi +2 more
2024Proc. ACM Program. Lang.36 citations Open access
Semantic Scholar
Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study
Yi Liu, Zhi-Hao Chen, Yan-Jun Zhang, Ge-Lei Deng +3 more
2026arXiv.org34 citations
Semantic Scholar
IllusionCAPTCHA: A CAPTCHA based on Visual Illusion
Zi-Qi Ding, Ge-Lei Deng, Yi Liu, Junchen Ding +3 more
2025The Web Conference27 citations Open access
Semantic Scholar
How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
Zhi-Hao Chen, Ying Zhang, Yi Liu, Ge-Lei Deng +6 more
2026Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering20 citations Open access
Semantic Scholar
Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
Yu-Xi Li, Yi Liu, Yuekang Li, Ling Shi +3 more
2024International Conference on Pattern Recognition20 citations Open access
Semantic Scholar
Genetic architecture of sugarcane traits in a polyploid genomics framework
Jungang Wang, Xiaofen Li, Yibin Wang, Ji-Shan Lin +42 more
2026Nature18 citations Open access
Semantic Scholar
MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation
Guan-Yu Wang, Yuekang Li, Yi Liu, Ge-Lei Deng +5 more
20242024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering (Forge) Conference Acronym:18 citations Open access
Semantic Scholar
Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
Yu-Bin Qu, Ying Zhang, Yan-Jun Zhang, Ge-Lei Deng +3 more
2026arXiv.org17 citations
Semantic Scholar
Image-Based Geolocation Using Large Vision-Language Models
Yi Liu, Junchen Ding, Ge-Lei Deng, Yuekang Li +5 more
2024arXiv.org15 citations
Semantic Scholar
JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models
Jian-Yi Hu, Hang Zhang, Yi Liu, Ye-Qi Zeng +4 more
202614 citations
Semantic Scholar
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Ruo-Qi Guo, Yi Liu, Ge-Lei Deng, Yue-Kang Li +5 more
202612 citations
Semantic Scholar
StepAudio 2.5 Technical Report
Bin Lin, Bo Zhao, Boyong Wu, Chao Yan +97 more
202611 citations
Semantic Scholar
GeneRAG: Enhancing Large Language Models with Gene-Related Task by Retrieval-Augmented Generation
Xinyi Lin, Ge-Lei Deng, Yuekang Li, Jing-Quan Ge +2 more
2024bioRxiv10 citations Open access
Semantic Scholar
Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
Zhi-Hao Chen, Ying Zhang, Yi Liu, Ge-Lei Deng +6 more
2026arXiv.org5 citations
Semantic Scholar
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Si-Qi Cai, Shao-Peng Chen, Xiang Fei, Yong Mao +33 more
2026arXiv.org5 citations
Semantic Scholar
Toward Efficient Membership Inference Attacks Against Federated Large Language Models: A Projection Residual Approach
Gui-Lin Deng, Si-Long Chen, Yu-Chuan Luo, Yi Liu +5 more
2026IEEE Symposium on Security and Privacy4 citations
Semantic Scholar
A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories
Zi-Qi Ding, Qian Fu, Junchen Ding, Ge-Lei Deng +2 more
20252025 IEEE Security and Privacy Workshops (SPW)4 citations Open access
Semantic Scholar
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
Yue Wang, Yi Liu, Ge-Lei Deng, Ying Zhang +3 more
20263 citations
Semantic Scholar
Integrated transcriptomic and metabolomic analyses reveal the molecular mechanisms underlying the improvement of muscle quality in grass carp (Ctenopharyngodon idellus) following 30-week nano-selenium supplementation.
Pin-Pin Zhang, Ming-Peng Zheng, Min-Min Xie, Yixuan Chen +3 more
2026Fish Physiology & Biochemistry3 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
Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
Zi-Hao Xu, Yi Liu, Ge-Lei Deng, Kai-Long Wang +3 more
20242025 IEEE Security and Privacy Workshops (SPW)2 citations Open access
Semantic Scholar
MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
Ruo-Qi Guo, Yi Liu, Ge-Lei Deng, Yiheng Xiong +6 more
2026arXiv.org1 citations
Semantic Scholar
Mind your key: An Empirical Study of LLM API Credential Leakage in iOS Apps
Pin Gao, Ling-Xiang Wang, Yi Liu, Kun Liu +2 more
2026arXiv.org1 citations
Semantic Scholar
SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
Yu-Bin Qu, Yi Liu, Ge-Lei Deng, Yan-Jun Zhang +3 more
2026arXiv.org1 citations
Semantic Scholar
One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents
Chao-Liang Yan, Zi-Hao Xu, Yue-Kang Li, Shang-Zhi Xu +3 more
20261 citations
Semantic Scholar
CognixShield: PoV-Guided Vulnerable API Usage Detection in Large Codebases via LLMs
Quanzhi Fu, Ling-Xiang Wang, Wenjia Song, Ge-Lei Deng +3 more
20251 citations
Semantic Scholar
Indiana Jones: There Are Always Some Useful Ancient Relics
Junchen Ding, Jia-Hao Zhang, Yi Liu, Zi-Qi Ding +2 more
2025arXiv.org1 citations
Semantic Scholar
TombRaider: Entering the Vault of History to Jailbreak Large Language Models
Junchen Ding, Jia-Hao Zhang, Yi Liu, Zi-Qi Ding +2 more
2025Conference on Empirical Methods in Natural Language Processing1 citations Open access
Semantic Scholar
Membership Inference Attacks Against Video Large Language Models
Wei Song, Yu-Xin Cao, Zi-Qi Ding, Yi Liu +2 more
2026arXiv.org0 citations
Semantic Scholar
Robust CAPTCHA Using Audio Illusions in the Era of Large Language Models: from Evaluation to Advances
Zi-Qi Ding, Yunfeng Wan, Wei Song, Yi Liu +6 more
2026arXiv.org0 citations
Semantic Scholar
Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code
Zi-Hao Xu, Yue-Kang Li, Ge-Lei Deng, Yi Liu +1 more
2026arXiv.org0 citations
Semantic Scholar
A QoS-Aware Hierarchical UAV–MEC Communication Network in Electric Vehicle Aggregation and Control
Xin Wu, Xinyu Jiang, Yanbing Li, Lin Liu +2 more
2026IEEE Internet of Things Journal0 citations
Semantic Scholar
AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
Junchen Ding, Jialiang Dong, Yi Zhu, Yi Liu +4 more
20260 citations
Semantic Scholar
SAF: An AI-Agent-Ready and Browser-Accessible Static Analysis Framework for LLVM IR
Yue-Kang Li, Wei Li, Wei Song, Yi Liu +1 more
2026Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering0 citations Open access
Semantic Scholar
MLSTM: A GraphSAGE-based Android Malware Detection Method Integrating Mean Aggregation and LSTM
Yi Liu, M. Johar, Jacquline Tham
2026Informatica0 citations Open access
Semantic Scholar
A Methodology for Replicating Historical Exploits on EVM-Compatible Blockchains
Zhiyang Chen, Phillip Kemper, Yi Liu, Jan Gorzny +4 more
2025International Workshop on Emerging Trends in Software Engineering for Blockchain0 citations Open access
Semantic Scholar
This paper is included in the Proceedings of the 32nd USENIX Security Symposium.
Ge-Lei Deng, Yuekang Li, Yi Liu, Tian-Wei Zhang +4 more
0 citations
Semantic Scholar
Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Anonymous ACL submission
Cem Anil, Esin Durmus, Nina Rimsky, Mrinank +126 more
0 citations
Semantic Scholar

Frequent co-authors

Invite them to SciRah by sharing their profile.

Ge-Lei Deng×34
Invite
Ge-Lei Deng — researcher profile on SciRah
Yue-Kang Li×20
Invite
Yue-Kang Li — researcher profile on SciRah
Yuekang Li×14
Invite
Yuekang Li — researcher profile on SciRah
L. Zhang×12
Invite
L. Zhang — researcher profile on SciRah

×10

Invite

Ying Zhang — researcher profile on SciRah

Junchen Ding×7

Invite

Junchen Ding — researcher profile on SciRah

Yan-Jun Zhang×6

Invite

Yan-Jun Zhang — researcher profile on SciRah

Invite

Zi-Qi Ding — researcher profile on SciRah

Tian-Wei Zhang×5

Invite

Tian-Wei Zhang — researcher profile on SciRah

Invite

Zi-Hao Xu — researcher profile on SciRah

Invite

Yang Liu — researcher profile on SciRah

Kai-Long Wang×4

Invite

Kai-Long Wang — researcher profile on SciRah