8 papers
Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs
Tao Lin, Gaojie Jin, Zongxin Liu +2
Existing vision-language model (VLM) backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets bef…
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
Gaojie Jin, Yong Tao, Lijia Yu +1
Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models (LLMs) and human judgments, relying on the assumption that the…
BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
Shuaitong Liu, Renjue Li, Lijia Yu +3
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computati…
Analyzing the Power of Chain of Thought through Memorization Capabilities
Lijia Yu, Xiao-Shan Gao, Lijun Zhang
It has been shown that the chain of thought (CoT) can enhance the power of large language models (LLMs) to solve certain mathematical reasoning problems. However, the capacity of C…
SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
Xiaonan Si, Meilin Zhu, Simeng Qin +7
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which ca…
Provable Watermarking for Data Poisoning Attacks
Yifan Zhu, Lijia Yu, Xiao-Shan Gao
In recent years, data poisoning attacks have been increasingly designed to appear harmless and even beneficial, often with the intention of verifying dataset ownership or safeguard…