Get started
Author

Zhaoxia Yin

Observed name: Yin, Zhaoxia
Observed institution: East China Normal University
OpenAlex ID: A5108322574
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
2026 · Xie, Yi, Du, Jiawei, et al. · arXiv (Cornell University)
PDF
VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
2026 · Cheng, Xin, Kong, Cong, et al. · arXiv (Cornell University)
PDF
LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks
2026 · Wan, Jiayong, Chen, Jiawei, et al. · arXiv (Cornell University)
PDF
Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
2026 · Chen, Jiawei, Huang, Simin, et al. · arXiv (Cornell University)
PDF
Red Teaming Large Reasoning Models
2026 · Jiawei Chen, Yang Yang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
2026 · Yu Cheng, Yongkang Hu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks
2026 · Jiayong Wan, Jiawei Chen, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs
2025 · Jiawei Chen, Xiao Yang, et al. · Findings of the Association for Computational Linguistics: NAACL
PDF
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
2024 · Chen, Jiawei, Yang, Xiao, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count:
H-index:
I10-index:
Year
Topic
Type