security risks

4 papers

• FedRACE: A Hierarchical and Statistical Framework for Robust Federated Learning
• Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
• Scalable Fingerprinting of Large Language Models
• Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers