6 papers
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…
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…
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…
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…
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,…
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…