首页/论文/2001.04942

arXiv 2001.049422020-01cs.LGstat.ML

Private Machine Learning via Randomised Response

University College London（伦敦大学学院）；Department of Computer Science（计算机科学系）

David Barber

英文摘要：

We introduce a general learning framework for private machine learning based on randomised response. Our assumption is that all actors are potentially adversarial and as such we trust only to release a single noisy version of an individual's datapoint. We discuss a general approach that forms a consistent way to estimate the true underlying machine learning model and demonstrate this in the case of logistic regression.

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。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

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。

继续探索

相关论文

Private Sequential Learning

Massachusetts Institute of Technology（麻省理工学院）；Stanford University（斯坦福大学）

We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, $v^*$, by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes the learner's queries, though not the responses, and tries to infer from them the value of $v^*$. The objective of the learner is to obtain an accurate estimate of $v^*$ using only a small number of queries, while simultaneously protecting her privacy by making $v^*$ provably di…

2020-02-26cs.LGstat.ML

私有、高效且可扩展的医学图像分析核学习

Private, Efficient and Scalable Kernel Learning for Medical Image Analysis

Department of Computer Science, Leipzig University（莱比锡大学计算机科学系）；Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)（可扩展数据与人工智能研究中心（ScaDS.AI））；Medical Data Privacy and Privacy-preserving Machine Learning (MDPPML)（医疗数据隐私与隐私保护机器学习（MDPPML））；Institute for Bioinformatics and Medical Informatics (IBMI)（生物信息学与医学信息学研究所）

针对医学图像分析中核方法面临的隐私和高维挑战，提出基于随机编码的OKRA方法，提升可扩展性和速度，并在临床数据集上优于现有方法。

2024-10-21cs.CRcs.LG

从人类响应数据中进行最优且私密的学习

Optimal and Private Learning from Human Response Data

University of Pennsylvania（宾夕法尼亚大学）

针对项目反应理论中的Rasch模型，本文改进了谱估计算法的误差界并证明其最优样本复杂度，同时首次提出隐私保护扩展，利用离散高斯机制实现低中隐私下的高精度学习。

2023-11-11cs.LG

Optimal query complexity for private sequential learning against eavesdropping

The Fuqua School of Business, Duke University（杜克大学富卡商学院）；Stanford Graduate School of Business, Stanford University（斯坦福大学商学院）

We study the query complexity of a learner-private sequential learning problem, motivated by the privacy and security concerns due to eavesdropping that arise in practical applications such as pricing and Federated Learning. A learner tries to estimate an unknown scalar value, by sequentially querying an external database and receiving binary responses; meanwhile, a third-party adversary observes the learner's queries but not the responses. The learner's goal is to design a querying strategy with the minimum number of queries (optimal query complexity) so that she can accurately estimate the t…

2020-08-17cs.CRcs.LGstat.ML

差分隐私下的战略响应审计

Differentially Private Auditing Under Strategic Response

University of Bath（巴斯大学）

本文研究了在审计方与开发者战略响应下，差分隐私审计的设计问题，提出了一种考虑福利权重、审计误判概率、检测弹性及缓解成本曲率的四因素平衡模型，通过开发者KKT系统提出SPAD算法。

2026-08-03cs.CRcs.GTcs.LG

Test without Trust: Optimal Locally Private Distribution Testing

Cornell University（康奈尔大学）；Stanford University（斯坦福大学）；Indian Institute of Science（印度科学学院）

We study the problem of distribution testing when the samples can only be accessed using a locally differentially private mechanism and focus on two representative testing questions of identity (goodness-of-fit) and independence testing for discrete distributions. We are concerned with two settings: First, when we insist on using an already deployed, general-purpose locally differentially private mechanism such as the popular RAPPOR or the recently introduced Hadamard Response for collecting data, and must build our tests based on the data collected via this mechanism; and second, when no such…

2018-08-07cs.CRcs.DMcs.DS

更多相关论文收起更多论文

Locally Differentially-Private Randomized Response for Discrete Distribution Learning

Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA)（加泰罗尼亚电信技术中心（CTTC/CERCA））；Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）

We consider a setup in which confidential i.i.d. samples $X_1,\dotsc,X_n$ from an unknown finite-support distribution $\boldsymbol{p}$ are passed through $n$ copies of a discrete privatization channel (a.k.a. mechanism) producing outputs $Y_1,\dotsc,Y_n$. The channel law guarantees a local differential privacy of $ε$. Subject to a prescribed privacy level $ε$, the optimal channel should be designed such that an estimate of the source distribution based on the channel outputs $Y_1,\dotsc,Y_n$ converges as fast as possible to the exact value $\boldsymbol{p}$. For this purpose we study the conver…

2018-11-29cs.ITcs.LGmath.IT

HRNet：用于人类移动数据合成的差分隐私分层多分辨率网络

HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization

Kyoto University（京都大学）；Emory University（埃默里大学）；Tokyo Institute of Technology（东京工业大学）；Osaka Seikei University（大阪成蹊大学）

针对人类移动数据合成中的隐私问题，本文提出差分隐私分层多分辨率网络HRNet，通过分层编码、多任务学习和私有预训练，在真实数据集上显著提升了效用-隐私权衡。

2024-07-20cs.CRcs.LG

具有重尾响应的差分隐私稀疏线性回归

Differentially Private Sparse Linear Regression with Heavy-tailed Responses

Provable Responsible AI and Data Analytics (PRADA) Lab（可证明责任AI与数据分析实验室）；King Abdullah University of Science and Technology（卡布斯科学技术大学）；Utrecht University（乌得勒支大学）；University at Buffalo（布法罗大学）；Technical University Berlin（柏林技术大学）

本文研究高维重尾响应下的差分隐私稀疏线性回归，提出基于Huber损失与私有迭代硬阈值的DP-IHT-H和DP-IHT-L，改进误差界并在合成及真实数据上验证优势。

2025-06-07cs.CRcs.LG

面向大语言模型的隐私保护上下文学习

Privacy-Preserving In-Context Learning for Large Language Models

Princeton University（普林斯顿大学）

针对上下文示例可能被LLM响应泄露的问题，本文提出DP-ICL范式，通过不相交示例集上的模型集成与带噪共识生成差分隐私响应，并在分类和生成任务上验证了效用—隐私权衡。

2023-09-30cs.AIcs.CRcs.LG

Deep Learning with Label Differential Privacy

Google Research（谷歌研究院）；MIT（麻省理工学院）

The Randomized Response (RR) algorithm is a classical technique to improve robustness in survey aggregation, and has been widely adopted in applications with differential privacy guarantees. We propose a novel algorithm, Randomized Response with Prior (RRWithPrior), which can provide more accurate results while maintaining the same level of privacy guaranteed by RR. We then apply RRWithPrior to learn neural networks with label differential privacy (LabelDP), and show that when only the label needs to be protected, the model performance can be significantly improved over the previous state-of-t…

2021-10-26cs.DScs.LG

The Cost of Privacy in Asynchronous Differentially-Private Machine Learning

University of Melbourne（墨尔本大学）；Macquarie University（麦考瑞大学）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织 Data61）；Australian National University（澳大利亚国立大学）

We consider training machine learning models using Training data located on multiple private and geographically-scattered servers with different privacy settings. Due to the distributed nature of the data, communicating with all collaborating private data owners simultaneously may prove challenging or altogether impossible. In this paper, we develop differentially-private asynchronous algorithms for collaboratively training machine-learning models on multiple private datasets. The asynchronous nature of the algorithms implies that a central learner interacts with the private data owners one-on…

2020-06-29cs.CRcs.LGeess.SP

Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning

University of British Columbia（不列颠哥伦比亚大学）

Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol. However, this process assumes a trusted centralized infrastructure for coordination, and clients must trust that the central service does not use the byproducts of client data. In addition to this, a group of malicious clients could also harm the performance of the model by carrying out a poisoning attack. As a response, we propose Biscotti: a fully decentralized peer to peer (P…

2019-12-12cs.CRcs.DCcs.LG