Zidi Xiong

5

Papers

146

Total Citations

Papers (5)

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

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models