Zhen Xiang

3
Papers
162
Total Citations

Papers (3)

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

ICLR 2024
80
citations

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

ICML 2025
66
citations

Memory Injection Attacks on LLM Agents via Query-Only Interaction

NeurIPS 2025arXiv
16
citations