collaborators

7 papers

cs.CV2025

An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs

Zhi Luo, Zenghui Yuan, Wenqi Wei +2

With the remarkable success of Vision-Language Models (VLMs) on multimodal tasks, concerns regarding their deployment efficiency have become increasingly prominent. In particular,…

cs.CL2025

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

Guiyao Tie, Zenghui Yuan, Zeli Zhao +11

Self-correction of large language models (LLMs) emerges as a critical component for enhancing their reasoning performance. Although various self-correction methods have been propos…

cs.CR2025

Prompt Injection Attack to Tool Selection in LLM Agents

Jiawen Shi, Zenghui Yuan, Guiyao Tie +3

Tool selection is a key component of LLM agents. A popular approach follows a two-step process - \emph{retrieval} and \emph{selection} - to pick the most appropriate tool from a to…

cs.CR2025

Optimization-based Prompt Injection Attack to LLM-as-a-Judge

Jiawen Shi, Zenghui Yuan, Yinuo Liu +4

LLM-as-a-Judge uses a large language model (LLM) to select the best response from a set of candidates for a given question. LLM-as-a-Judge has many applications such as LLM-powered…

cs.CR2025

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

Zenghui Yuan, Yangming Xu, Jiawen Shi +2

Model merging for Large Language Models (LLMs) directly fuses the parameters of different models finetuned on various tasks, creating a unified model for multi-domain tasks. Howeve…

cs.CR2025

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

Zenghui Yuan, Jiawen Shi, Pan Zhou +2

Multi-modal large language models (MLLMs) extend large language models (LLMs) to process multi-modal information, enabling them to generate responses to image-text inputs. MLLMs ha…