13 papers
When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems
Chenqing Zhu, Yanbo Dai, Yulong Tian +2
Large Language Model (LLM)-based question-answering (QA) systems are increasingly deployed in sensitive domains such as healthcare, mental health counseling, and legal consultation…
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
Mingxuan Zhang, Jiahui Han, Dadi Guo +5
LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire more sensitive information than t…
Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models
Kai Wang, Jiale Zhang, Chengcheng Zhu +2
Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus m…
When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
Zehan Sun, Dingfan Chen, Songze Li
Large Language Model (LLM) cascade systems are designed to balance efficiency and performance by processing queries with lightweight models while selectively escalating complex cas…
Unveiling the Security Risks of Federated Learning in the Wild: From Research to Practice
Jiahao Chen, Zhiming Zhao, Yuwen Pu +4
Federated learning (FL) has attracted substantial attention in both academia and industry, yet its practical security posture remains poorly understood. In particular, a large body…
Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models
Sizai Hou, Songze Li, Baturalp Buyukates
Prompt learning is a crucial technique for adapting pre-trained multimodal language models (MLLMs) to user tasks. Federated prompt personalization (FPP) is further developed to add…