Safe-FedLLM: Delving into the Safety of Federated Large Language Models
Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM). However, security in open federated environments, particularly defenses against malicious clients, remains underexplored. To investigate the security of FedLLM, we conduct a preliminary study to analyze potential attack surfaces and defensive characteristics from the perspective of LoRA updates. We find two key properties of FedLLM: 1) LLMs are vulnerable to attacks from malicious clients in FL, and 2) LoRA updates exhibit distinct behavioral patterns that can be effectively distinguished by lightweight classifiers. Based on these properties, we propose Safe-FedLLM, a probe-based defense framework for FedLLM, which constructs defenses across three levels: Step-Level, Client-Level, and Shadow-Level. The core concept of Safe-FedLLM is to perform probe-based discrimination on each client's local LoRA updates, treating them as high-dimensional behavioral features and using a lightweight classifier to determine whether they are malicious. Extensive experiments demonstrate that Safe-FedLLM effectively improves FedLLM's robustness against malicious clients while maintaining competitive performance on benign data. Notably, our method effectively suppresses the impact of malicious data without significantly affecting training speed, and remains effective even under high malicious client ratios.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Toward Responsible Federated Large Language Models: Leveraging a Safety Filter and Constitutional AI
Recent research has increasingly focused on training large language models (LLMs) using federated learning, known as FedLLM. However, responsible AI (RAI), which aims to ensure safe responses, remains underexplored in th…
Federated LearningFederated Fine-Tuning of LLMs: Framework Comparison and Research Directions
Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets, enabling task-specific adaptation while preserving data privacy.…
Federated LearningKnowledge DistillationPrivacy PreservingFedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
Federated learning has enabled multiple parties to collaboratively train large language models without directly sharing their data (FedLLM). Following this training paradigm, the community has put massive efforts from di…
Federated LearningFedLLM-Align: Feature Extraction From Heterogeneous Clients
Federated learning (FL) enables collaborative model training without sharing raw data, making it attractive for privacy-sensitive domains, e.g., healthcare, finance, and IoT. A major obstacle, however, is the potential h…
Binary ClassificationFederated LearningA Survey on Federated Fine-tuning of Large Language Models
Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, with fine-tuning playing a pivotal role in adapting them to specific downstream applications. Federated Learning (FL) offers a p…
Federated Learningparameter-efficient fine-tuningPrivacy PreservingSurvey