Get started
Author

Yuekai Huang

Beyond Static GUI Agent: Evolving LLM-based GUI Testing via Dynamic Memory
2025 · Mengzhuo Chen, Zhe Liu, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE) · 3
Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
2026 · Haowei Wang, Rupeng Zhang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
PDF
CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems
2026 · Zheng, Yujia, Li, Tianhao, et al. · arXiv (Cornell University)
PDF
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
2026 · Association for Computational Linguistics 2026, Chang, Zhiyuan, et al. · Underline Science Inc.
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
2026 · Association for Computational Linguistics 2026, Chang, Zhiyuan, et al. · Underline Science Inc.
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs
2026 · Association for Computational Linguistics 2026, Chu, Chuangxin, et al. · Underline Science Inc.
Emerging from Ground: Addressing Intent Deviation in Tool-Using Agents via Deriving Real Calls into Virtual Trajectories
2026 · Xiong, Qian, Huang, Yuekai, et al. · arXiv (Cornell University)
PDF
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
2026 · Jiang, Ziyou, Li, Mingyang, et al. · arXiv (Cornell University)
PDF
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
2026 · Chang, Zhiyuan, Li, Mingyang, et al. · arXiv (Cornell University)
PDF
Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
2026 · Association for Artificial Intelligence 2026, Huang, Yuekai, et al. · Underline Science Inc.
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs
2026 · Yujia Zheng, Tianhao Li, et al. · Conference of the European Chapter of the Association for Computational Linguistics
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
2026 · Zhiyuan Chang, Mingyang Li, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
2026 · Ziyou Jiang, Mingyang Li, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 15
Citation count: 4
H-index: 1
I10-index:
Year
Topic
Type