Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-enabled Critical Infrastructure

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Deng, Zehang, Sun, Ruoxi, Xue, Minhui, Wen, Sheng, Camtepe, Seyit, Nepal, Surya, Xiang, Yang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909209955663872
author Deng, Zehang
Sun, Ruoxi
Xue, Minhui
Wen, Sheng
Camtepe, Seyit
Nepal, Surya
Xiang, Yang
author_facet Deng, Zehang
Sun, Ruoxi
Xue, Minhui
Wen, Sheng
Camtepe, Seyit
Nepal, Surya
Xiang, Yang
contents AI-enabled critical infrastructures (ACIs) integrate artificial intelligence (AI) technologies into various essential systems and services that are vital to the functioning of society, offering significant implications for efficiency, security and resilience. While adopting decentralized AI approaches (such as federated learning technology) in ACIs is plausible, private and sensitive data are still susceptible to data reconstruction attacks through gradient optimization. In this work, we propose Compressed Differentially Private Aggregation (CDPA), a leakage-resilient, communication-efficient, and carbon-neutral approach for ACI networks. Specifically, CDPA has introduced a novel random bit-flipping mechanism as its primary innovation. This mechanism first converts gradients into a specific binary representation and then selectively flips masked bits with a certain probability. The proposed bit-flipping introduces a larger variance to the noise while providing differentially private protection and commendable efforts in energy savings while applying vector quantization techniques within the context of federated learning. The experimental evaluation indicates that CDPA can reduce communication cost by half while preserving model utility. Moreover, we demonstrate that CDPA can effectively defend against state-of-the-art data reconstruction attacks in both computer vision and natural language processing tasks. We highlight existing benchmarks that generate 2.6x to over 100x more carbon emissions than CDPA. We hope that the CDPA developed in this paper can inform the federated AI-enabled critical infrastructure of a more balanced trade-off between utility and privacy, resilience protection, as well as a better carbon offset with less communication overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15258
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-enabled Critical Infrastructure
Deng, Zehang
Sun, Ruoxi
Xue, Minhui
Wen, Sheng
Camtepe, Seyit
Nepal, Surya
Xiang, Yang
Cryptography and Security
AI-enabled critical infrastructures (ACIs) integrate artificial intelligence (AI) technologies into various essential systems and services that are vital to the functioning of society, offering significant implications for efficiency, security and resilience. While adopting decentralized AI approaches (such as federated learning technology) in ACIs is plausible, private and sensitive data are still susceptible to data reconstruction attacks through gradient optimization. In this work, we propose Compressed Differentially Private Aggregation (CDPA), a leakage-resilient, communication-efficient, and carbon-neutral approach for ACI networks. Specifically, CDPA has introduced a novel random bit-flipping mechanism as its primary innovation. This mechanism first converts gradients into a specific binary representation and then selectively flips masked bits with a certain probability. The proposed bit-flipping introduces a larger variance to the noise while providing differentially private protection and commendable efforts in energy savings while applying vector quantization techniques within the context of federated learning. The experimental evaluation indicates that CDPA can reduce communication cost by half while preserving model utility. Moreover, we demonstrate that CDPA can effectively defend against state-of-the-art data reconstruction attacks in both computer vision and natural language processing tasks. We highlight existing benchmarks that generate 2.6x to over 100x more carbon emissions than CDPA. We hope that the CDPA developed in this paper can inform the federated AI-enabled critical infrastructure of a more balanced trade-off between utility and privacy, resilience protection, as well as a better carbon offset with less communication overhead.
title Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-enabled Critical Infrastructure
topic Cryptography and Security
url https://arxiv.org/abs/2405.15258