Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
- URL: http://arxiv.org/abs/2406.14898v2
- Date: Wed, 26 Jun 2024 04:28:38 GMT
- Title: Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
- Authors: JiaYing Zheng, HaiNan Zhang, LingXiang Wang, WangJie Qiu, HongWei Zheng, ZhiMing Zheng,
- Abstract summary: Federated learning (FL) is an ideal solution for training models with distributed private data.
Traditional frameworks like FedAvg are unsuitable for large language models (LLM)
We propose FL-GLM, which prevents data leakage caused by both server-side and peer-client attacks.
- Score: 3.1077263218029105
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Private data, being larger and quality-higher than public data, can greatly improve large language models (LLM). However, due to privacy concerns, this data is often dispersed in multiple silos, making its secure utilization for LLM training a challenge. Federated learning (FL) is an ideal solution for training models with distributed private data, but traditional frameworks like FedAvg are unsuitable for LLM due to their high computational demands on clients. An alternative, split learning, offloads most training parameters to the server while training embedding and output layers locally, making it more suitable for LLM. Nonetheless, it faces significant challenges in security and efficiency. Firstly, the gradients of embeddings are prone to attacks, leading to potential reverse engineering of private data. Furthermore, the server's limitation of handle only one client's training request at a time hinders parallel training, severely impacting training efficiency. In this paper, we propose a Federated Learning framework for LLM, named FL-GLM, which prevents data leakage caused by both server-side and peer-client attacks while improving training efficiency. Specifically, we first place the input block and output block on local client to prevent embedding gradient attacks from server. Secondly, we employ key-encryption during client-server communication to prevent reverse engineering attacks from peer-clients. Lastly, we employ optimization methods like client-batching or server-hierarchical, adopting different acceleration methods based on the actual computational capabilities of the server. Experimental results on NLU and generation tasks demonstrate that FL-GLM achieves comparable metrics to centralized chatGLM model, validating the effectiveness of our federated learning framework.
Related papers
- Boosting Communication Efficiency of Federated Learning's Secure Aggregation [22.943966056320424]
Federated Learning (FL) is a decentralized machine learning approach where client devices train models locally and send them to a server.
FL is vulnerable to model inversion attacks, where the server can infer sensitive client data from trained models.
Google's Secure Aggregation (SecAgg) protocol addresses this data privacy issue by masking each client's trained model.
This poster introduces a Communication-Efficient Secure Aggregation (CESA) protocol that substantially reduces this overhead.
arXiv Detail & Related papers (2024-05-02T10:00:16Z) - Blockchain-enabled Trustworthy Federated Unlearning [50.01101423318312]
Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients.
Existing works require central servers to retain the historical model parameters from distributed clients.
This paper proposes a new blockchain-enabled trustworthy federated unlearning framework.
arXiv Detail & Related papers (2024-01-29T07:04:48Z) - HierSFL: Local Differential Privacy-aided Split Federated Learning in
Mobile Edge Computing [7.180235086275924]
Federated Learning is a promising approach for learning from user data while preserving data privacy.
Split Federated Learning is utilized, where clients upload their intermediate model training outcomes to a cloud server for collaborative server-client model training.
This methodology facilitates resource-constrained clients' participation in model training but also increases the training time and communication overhead.
We propose a novel algorithm, called Hierarchical Split Federated Learning (HierSFL), that amalgamates models at the edge and cloud phases.
arXiv Detail & Related papers (2024-01-16T09:34:10Z) - Subspace based Federated Unlearning [75.90552823500633]
Federated unlearning (FL) aims to remove a specified target client's contribution in FL to satisfy the user's right to be forgotten.
Most existing federated unlearning algorithms require the server to store the history of the parameter updates.
We propose a simple-yet-effective subspace based federated unlearning method, dubbed SFU, that lets the global model perform gradient ascent.
arXiv Detail & Related papers (2023-02-24T04:29:44Z) - Scalable Collaborative Learning via Representation Sharing [53.047460465980144]
Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device)
In FL, each data holder trains a model locally and releases it to a central server for aggregation.
In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation).
In this work, we present a novel approach for privacy-preserving machine learning, where the clients collaborate via online knowledge distillation using a contrastive loss.
arXiv Detail & Related papers (2022-11-20T10:49:22Z) - Optimizing Server-side Aggregation For Robust Federated Learning via
Subspace Training [80.03567604524268]
Non-IID data distribution across clients and poisoning attacks are two main challenges in real-world federated learning systems.
We propose SmartFL, a generic approach that optimize the server-side aggregation process.
We provide theoretical analyses of the convergence and generalization capacity for SmartFL.
arXiv Detail & Related papers (2022-11-10T13:20:56Z) - Efficient and Privacy Preserving Group Signature for Federated Learning [2.121963121603413]
Federated Learning (FL) is a Machine Learning (ML) technique that aims to reduce the threats to user data privacy.
This paper proposes an efficient and privacy-preserving protocol for FL based on group signature.
arXiv Detail & Related papers (2022-07-12T04:12:10Z) - FLVoogd: Robust And Privacy Preserving Federated Learning [12.568409209047505]
We proposeoogd, an updated federated learning method in which servers and clients collaboratively eliminate Byzantine attacks while preserving privacy.
Servers use automatic Density-based Spatial Clustering of Applications with Noise (DBSCAN) combined with S2PC to cluster the benign majority without acquiring sensitive personal information.
Our framework is automatic and adaptive that servers/clients don't need to tune the parameters during the training.
arXiv Detail & Related papers (2022-06-24T08:48:15Z) - Acceleration of Federated Learning with Alleviated Forgetting in Local
Training [61.231021417674235]
Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy.
We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage.
Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
arXiv Detail & Related papers (2022-03-05T02:31:32Z) - Blockchain Assisted Decentralized Federated Learning (BLADE-FL):
Performance Analysis and Resource Allocation [119.19061102064497]
We propose a decentralized FL framework by integrating blockchain into FL, namely, blockchain assisted decentralized federated learning (BLADE-FL)
In a round of the proposed BLADE-FL, each client broadcasts its trained model to other clients, competes to generate a block based on the received models, and then aggregates the models from the generated block before its local training of the next round.
We explore the impact of lazy clients on the learning performance of BLADE-FL, and characterize the relationship among the optimal K, the learning parameters, and the proportion of lazy clients.
arXiv Detail & Related papers (2021-01-18T07:19:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.