4 papers
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
Xi Li, Shu Zhao, Xiaohan Zou +6
Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this arc…
NeuroGen: Neural Network Parameter Generation via Large Language Models
Jiaqi Wang, Yusen Zhang, Xi Li
Acquiring the parameters of neural networks (NNs) has been one of the most important problems in machine learning since the inception of NNs. Traditional approaches, such as backpr…
Securing Federated Learning against Backdoor Threats with Foundation Model Integration
Xiaohuan Bi, Xi Li
Federated Learning (FL) enables decentralized model training while preserving privacy. Recently, the integration of Foundation Models (FMs) into FL has enhanced performance but int…
Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
Xi Li, Ruofan Mao, Yusen Zhang +3
Large Language Models (LLMs), especially those accessed via APIs, have demonstrated impressive capabilities across various domains. However, users without technical expertise often…