collaborators

6 papers

cs.CR2026

A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG

Junjie Mu, Qiongxiu Li

Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because raw data remain local. As a result, routing must rely on client-provided…

cs.CL2026

Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups

Geng Liu, Feng Li, Junjie Mu +2

Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they may reflect and amplify social biases. We investigate social identity…

cs.LG2026

Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection

Weilin Zhou, Zonghao Ying, Rongchen Zhao +7

Prevalent multimodal fake news detection relies on consistency-based fusion, yet this paradigm fundamentally misinterprets critical cross-modal discrepancies as noise, leading to o…

cs.CL2026

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?

Junjie Mu, Zonghao Ying, Zhekui Fan +6

Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are d…

cs.CR2025

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions

Zonghao Ying, Le Wang, Yisong Xiao +7

The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands,…

cs.CR2025

Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling

Deyue Zhang, Dongdong Yang, Junjie Mu +6

Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal vulnerabilities. In this work, we introd…