collaborators

11 papers

cs.CL2026

Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics

Qingjie Zhang, Ziqi Tang, Jie Zhang +7

Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size makes ful…

cs.CR2026

Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure

Jianshuo Dong, Yiming Liu, Maosen Zhang +6

Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While many efforts have sought to address the th…

cs.AI2026

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents

Jianshuo Dong, Sheng Guo, Hao Wang +6

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search r…

cs.CR2026

LeakDojo: Decoding the Leakage Threats of RAG Systems

Maosen Zhang, Jianshuo Dong, Boting Lu +4

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to leverage external knowledge, but also exposes valuable RAG databases to leakage attacks. As RAG systems…

cs.CL2025

Speculating LLMs' Chinese Training Data Pollution from Their Tokens

Qingjie Zhang, Di Wang, Haoting Qian +7

Tokens are basic elements in the datasets for LLM training. It is well-known that many tokens representing Chinese phrases in the vocabulary of GPT (4o/4o-mini/o1/o3/4.5/4.1/o4-min…

cs.CL2025

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models

Cheng Wang, Gelei Deng, Xianglin Yang +2

Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and te…