Shuaitong Liu — accepted AI-conference papers

2026

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models

Shuaitong Liu, Renjue Li, Lijia Yu, Lijun Zhang, Zhiming Liu, Gaojie Jin

AAAI 2026technical

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we propose BadThink, the first backdoor attack designed to delib

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG

Xiaonan si, Meilin Zhu, Simeng Qin, Lijia Yu, Lijun Zhang, Shuaitong Liu +4

NeurIPS 2025poster

Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which can compromise output integrity. Existing defenses often apply aggressive filtering, leading to unnecessary loss of valuab…

Cited by 0 Source ↗Scholar ↗