paper-with-me

홈 › Papers

$Λ$-Split: A Privacy-Preserving Split Computing Framework for Cloud-Powered Generative AI

2023-10-23 · Shoki Ohta, Takayuki Nishio

In the wake of the burgeoning expansion of generative artificial intelligence (AI) services, the computational demands inherent to these technologies frequently necessitate cloud-powered computational offloading, particularly for resource-constrained mobile devices. These services commonly employ prompts to steer the generative process, and both the prompts and the resultant content, such as text and images, may harbor privacy-sensitive or confidential information, thereby elevating security and privacy risks. To mitigate these concerns, we introduce $\Lambda$-Split, a split computing framework to facilitate computational offloading while simultaneously fortifying data privacy against risks such as eavesdropping and unauthorized access. In $\Lambda$-Split, a generative model, usually a deep neural network (DNN), is partitioned into three sub-models and distributed across the user's local device and a cloud server: the input-side and output-side sub-models are allocated to the local, while the intermediate, computationally-intensive sub-model resides on the cloud server. This architecture ensures that only the hidden layer outputs are transmitted, thereby preventing the external transmission of privacy-sensitive raw input and output data. Given the black-box nature of DNNs, estimating the original input or output from intercepted hidden layer outputs poses a significant challenge for malicious eavesdroppers. Moreover, $\Lambda$-Split is orthogonal to traditional encryption-based security mechanisms, offering enhanced security when deployed in conjunction. We empirically validate the efficacy of the $\Lambda$-Split framework using Llama 2 and Stable Diffusion XL, representative large language and diffusion models developed by Meta and Stability AI, respectively. Our $\Lambda$-Split implementation is publicly accessible at https://github.com/nishio-laboratory/lambda_split.

📄 PDF Abstract BibTeX arXiv:2310.14651

Code (1)

nishio-laboratory/lambda_split 공식 구현 pytorch

Tasks

Privacy Preserving

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Spatio-Temporal Split Learning

2021-08-13 · Joongheon Kim, Seunghoon Park, Soyi Jung, Seehwan Yoo

This paper proposes a novel split learning framework with multiple end-systems in order to realize privacypreserving deep neural network computation. In conventional split learning frameworks, deep neural network computa…

P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices

2025-07-23 · Wei Fan, JinYi Yoon, Xiaochang Li, Huajie Shao 외 arxiv

Split Learning (SL) is an emerging privacy-preserving machine learning technique that enables resource constrained edge devices to participate in model training by partitioning a model into client-side and server-side su…

Optimal Resource Allocation for U-Shaped Parallel Split Learning

2023-08-17 · Song Lyu, Zheng Lin, Guanqiao Qu, Xianhao Chen 외

Split learning (SL) has emerged as a promising approach for model training without revealing the raw data samples from the data owners. However, traditional SL inevitably leaks label privacy as the tail model (with the l…

Spatio-Temporal Split Learning for Privacy-Preserving Medical Platforms: Case Studies with COVID-19 CT, X-Ray, and Cholesterol Data

2021-08-20 · Yoo Jeong Ha, MinJae Yoo, Gusang Lee, Soyi Jung 외

Machine learning requires a large volume of sample data, especially when it is used in high-accuracy medical applications. However, patient records are one of the most sensitive private information that is not usually sh…

Computed Tomography (CT)Privacy Preserving

Split-n-Chain: Privacy-Preserving Multi-Node Split Learning with Blockchain-Based Auditability

2025-03-10 · Mukesh Sahani, Binanda Sengupta

Deep learning, when integrated with a large amount of training data, has the potential to outperform machine learning in terms of high accuracy. Recently, privacy-preserving deep learning has drawn significant attention …

Deep LearningFederated LearningPrivacy PreservingPrivacy Preserving Deep Learning