arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.16136cs.CRcs.AI
收藏

ERASER:通过推理服务感知方法实现MLaaS中的机器遗忘

ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach

Zhejiang University(浙江大学);Hong Kong University of Science and Technology(香港科技大学)

Yuke Hu, Jian Lou, Jiaqi Liu, Wangze Ni, Feng Lin, Zhan Qin, Kui Ren

AI总结:

本文提出ERASER框架,通过推理服务感知的遗忘执行时机选择和推理一致性认证机制,在MLaaS中同时解决机器遗忘引发的推理服务过时与RTBF违规隐私漏洞问题,实验证明可节省高达99%推理延迟和31%计算开销。

摘要:

在过去几年中,机器学习即服务(MLaaS)的需求激增,它支持机器学习驱动的服务,在各类应用领域中提供革命性的用户体验。MLaaS基于一个使用从众多个人数据所有者处收集的数据集训练而成的机器学习模型,提供低推理延迟的推理服务。近年来,为了数据所有者的隐私,并遵守数据保护法规所规定的“被遗忘权(RTBF)”,许多机器遗忘方法被提出,以便在收到数据所有者的遗忘请求后,从已训练模型中移除其数据。然而,尽管现有机器遗忘方法具有可观的效率,但几乎所有方法都将遗忘请求与推理请求独立处理,这不幸地引入了推理服务过时这一新的安全问题,以及MLaaS中机器遗忘不希望的数据暴露这一隐私漏洞。\n\n在本文中,我们提出了ERASER框架,用于通过推理服务感知方法实现MLaaS中的机器遗忘。ERASER策略性地选择合适的遗忘执行时机,以解决推理服务过时问题。我们提出了一种新颖的推理一致性认证机制,以避免因推迟遗忘执行而违反RTBF原则,从而缓解不希望的数据暴露漏洞。ERASER提供了三组设计选择,以便生成最适合各种MLaaS系统特定环境和偏好的定制化变体。跨多种设置的大量实证评估证实了ERASER的有效性,例如,与忽略推理的基线相比,它能够有效节省高达99%的推理延迟和31%的计算开销。

英文摘要:

Over the past years, Machine Learning-as-a-Service (MLaaS) has received a surging demand for supporting Machine Learning-driven services to offer revolutionized user experience across diverse application areas. MLaaS provides inference service with low inference latency based on an ML model trained using a dataset collected from numerous individual data owners. Recently, for the sake of data owners' privacy and to comply with the "right to be forgotten (RTBF)" as enacted by data protection legislation, many machine unlearning methods have been proposed to remove data owners' data from trained models upon their unlearning requests. However, despite their promising efficiency, almost all existing machine unlearning methods handle unlearning requests independently from inference requests, which unfortunately introduces a new security issue of inference service obsolescence and a privacy vulnerability of undesirable exposure for machine unlearning in MLaaS. In this paper, we propose the ERASER framework for machinE unleaRning in MLaAS via an inferencE seRving-aware approach. ERASER strategically choose appropriate unlearning execution timing to address the inference service obsolescence issue. A novel inference consistency certification mechanism is proposed to avoid the violation of RTBF principle caused by postponed unlearning executions, thereby mitigating the undesirable exposure vulnerability. ERASER offers three groups of design choices to allow for tailor-made variants that best suit the specific environments and preferences of various MLaaS systems. Extensive empirical evaluations across various settings confirm ERASER's effectiveness, e.g., it can effectively save up to 99% of inference latency and 31% of computation overhead over the inference-oblivion baseline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑