Get started
Author

Wenyu Chen

Observed name: Chen, Wenyu
Institution: Shandong University
Observed institution: Shandong University
OpenAlex ID: A5123331933
Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents
2026 · Gao, Xinyu, Chen, Wenyu, et al. · arXiv (Cornell University) · 3
PDF
Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
2026 · Chen, Wenyu, Meng, Xiangtao, et al. · arXiv (Cornell University) · 2
PDF
VidLeaks: Membership Inference Attacks Against Text-to-Video Models
2026 · Wang, Li, Chen, Wenyu, et al. · arXiv (Cornell University) · 2
PDF
One Risk Down, Another Up: Cross-Risk Interactions Induced by LLM Defenses
2025 · Meng, Xiangtao, Cong, Tianshuo, et al. · arXiv (Cornell University) · 1
PDF
Transferable End-to-End Optimization for Indirect Long-Term Memory Poisoning in LLM Agents
2026 · Zang, Chuanchao, Wang, Jianing, et al. · arXiv (Cornell University)
PDF
Extracting Knowledge from Tools in LLM Agents
2026 · Zang, Chuanchao, Wang, Jianing, et al. · arXiv (Cornell University)
PDF
Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory
2026 · Zang, Chuanchao, Cao, Zijian, et al. · arXiv (Cornell University)
PDF
Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models
2026 · Meng, Xiangtao, Chen, Wenyu, et al. · arXiv (Cornell University)
PDF
Works count: 8
Citation count: 8
H-index: 2
I10-index:
Year
Topic
Type