首页/论文/1603.08028

arXiv 1603.080282016-03-25cs.LGcs.CRcs.SI

On the Simultaneous Preservation of Privacy and Community Structure in Anonymized Networks

University of Illinois（伊利诺伊大学）；Princeton University（普林斯顿大学）

Daniel Cullina, Kushagra Singhal, Negar Kiyavash, Prateek Mittal

备注：: 10 pages

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We consider the problem of performing community detection on a network, while maintaining privacy, assuming that the adversary has access to an auxiliary correlated network. We ask the question "Does there exist a regime where the network cannot be deanonymized perfectly, yet the community structure could be learned?." To answer this question, we derive information theoretic converses for the perfect deanonymization problem using the Stochastic Block Model and edge sub-sampling. We also provide an almost tight achievability result for perfect deanonymization. We also evaluate the performance of percolation based deanonymization algorithm on Stochastic Block Model data-sets that satisfy the conditions of our converse. Although our converse applies to exact deanonymization, the algorithm fails drastically when the conditions of the converse are met. Additionally, we study the effect of edge sub-sampling on the community structure of a real world dataset. Results show that the dataset falls under the purview of the idea of this paper. There results suggest that it may be possible to prove stronger partial deanonymizability converses, which would enable better privacy guarantees.

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

Learning Anonymized Representations with Adversarial Neural Networks

Laboratoire des Signaux et Systèmes (L2S, UMR8506), CentraleSupélec-CNRS-Université Paris-Sud（信号与系统实验室（L2S，UMR8506），中央理工-高等电力学院-法国国家科学研究中心-巴黎第十一大学）；Montreal Institute for Learning Algorithms, Université de Montréal（蒙特利尔学习算法研究所，蒙特利尔大学）

Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. This paper investigates anonymization methods based on representation learning and deep neural networks, and motivated by novel information theoretical bounds. We introduce a novel training objective for simultaneously training a predictor over target variables of interest (the regular labels) while preventing an intermediate representation to be predictive of the private labels. The architecture is based on three sub-networks…

2018-02-26cs.CRcs.LGstat.ML

mvn2vec: Preservation and Collaboration in Multi-View Network Embedding

University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Snap Inc.（Snap公司）

Multi-view networks are broadly present in real-world applications. In the meantime, network embedding has emerged as an effective representation learning approach for networked data. Therefore, we are motivated to study the problem of multi-view network embedding with a focus on the optimization objectives that are specific and important in embedding this type of network. In our practice of embedding real-world multi-view networks, we explicitly identify two such objectives, which we refer to as preservation and collaboration. The in-depth analysis of these two objectives is discussed through…

2019-11-03cs.AIcs.LGcs.NE

Local and Global Structure Preservation Based Spectral Clustering

Tarbiat Modares University（塔比亚特·莫达雷斯大学）

Spectral Clustering (SC) is widely used for clustering data on a nonlinear manifold. SC aims to cluster data by considering the preservation of the local neighborhood structure on the manifold data. This paper extends Spectral Clustering to Local and Global Structure Preservation Based Spectral Clustering (LGPSC) that incorporates both global structure and local neighborhood structure simultaneously. For this extension, LGPSC proposes two models to extend local structures preservation to local and global structures preservation: Spectral clustering guided Principal component analysis model and…

2022-10-23cs.LG

DP-CDA：一种通过随机混合增强数据集合成隐私保护的算法

DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing

Department of Electrical and Electronic Engineering（电子与电气工程系）；Bangladesh University of Engineering Technology（孟加拉工程科技大学）

本文提出DP-CDA算法，通过随机混合敏感数据和引入可控随机性，在高维数据中实现更强的隐私保障与数据效用平衡。

2026-04-29cs.LGstat.ML

AnomiGAN: Generative adversarial networks for anonymizing private medical data

Seoul National University（首尔国立大学）

Typical personal medical data contains sensitive information about individuals. Storing or sharing the personal medical data is thus often risky. For example, a short DNA sequence can provide information that can not only identify an individual, but also his or her relatives. Nonetheless, most countries and researchers agree on the necessity of collecting personal medical data. This stems from the fact that medical data, including genomic data, are an indispensable resource for further research and development regarding disease prevention and treatment. To prevent personal medical data from be…

2019-01-31cs.CRcs.LG

Tempo：基于云的神经网络训练中的保密性保护

Tempo: Confidentiality Preservation in Cloud-Based Neural Network Training

IIIS, Tsinghua University（清华大学交叉信息研究院）

针对云端 DNN 训练的模型泄露风险，提出 Tempo 系统，结合 TEE 与分布式 GPU，通过置换混淆和加密优化实现保密且高效的训练。

2024-01-21cs.CRcs.LG

更多相关论文收起更多论文

情感保持说话人匿名化中的隐私与情感保留权衡

Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymization

Johns Hopkins University（约翰斯·霍普金斯大学）；Human Language Technology Center of Excellence（优秀人类语言技术中心）

本文在VoicePrivacy 2024挑战赛背景下研究情感保持说话人匿名化，发现匿名化与情感保持难以兼得，并证明仅用情感表征即可训练半有效的说话人验证系统，揭示了两种模态分离的困难。

2024-09-05cs.LGeess.AS

Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms

UBTECH Sydney AI Centre, School of Computer Science, Faculty of Engineering, the University of Sydney（悉尼大学工程学院计算机科学学院优必选悉尼人工智能中心）；University of Science and Technology of China（中国科学技术大学）

This paper studies the relationship between generalization and privacy preservation in iterative learning algorithms by two sequential steps. We first establish an alignment between generalization and privacy preservation for any learning algorithm. We prove that $(\varepsilon, δ)$-differential privacy implies an on-average generalization bound for multi-database learning algorithms which further leads to a high-probability bound for any learning algorithm. This high-probability bound also implies a PAC-learnable guarantee for differentially private learning algorithms. We then investigate how…

2020-08-07cs.CRcs.LGstat.ML

Deep Embedded Clustering with Distribution Consistency Preservation for Attributed Networks

Beijing Jiaotong University（北京交通大学）；Baidu Online Network Technology (Beijing) Co., Ltd（百度在线网络技术（北京）有限公司）

Many complex systems in the real world can be characterized by attributed networks. To mine the potential information in these networks, deep embedded clustering, which obtains node representations and clusters simultaneously, has been paid much attention in recent years. Under the assumption of consistency for data in different views, the cluster structure of network topology and that of node attributes should be consistent for an attributed network. However, many existing methods ignore this property, even though they separately encode node representations from network topology and node attr…

2022-05-28cs.AIcs.LG

ImprovDML：私有拜占庭弹性分布式机器学习中的改进权衡

ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning

针对分布式机器学习中拜占庭攻击与隐私泄露的联合挑战，提出ImprovDML框架，利用弹性向量共识和多元高斯噪声，在保证隐私与鲁棒性的同时提升模型准确率，并给出更紧的误差界，实现更优权衡。

2025-06-18cs.LG

FedMPDD: 一种通过投影方向导数实现通信高效联邦学习与隐私保护的方法

FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative

Department of Mechanical and Aerospace Engineering, University of California Irvine（加州大学尔湾分校机械与航空航天工程系）

FedMPDD通过投影方向导数在联邦学习中实现高效的通信和隐私保护，具有O(1/√K)的收敛速度和可调节的隐私-效用平衡。

2025-12-23cs.LG

微分方程的物理保持迁移学习方法

A Physics-preserved Transfer Learning Method for Differential Equations

Sun Yat-Sen University（中山大学）

针对微分方程求解中数据驱动模型面临的域偏移问题，提出物理保持最优张量传输（POTT）迁移学习方法，自适应纠正分布与算子偏差，兼具泛化性与物理保持，实验验证其优越性能。

2025-05-25cs.AIcs.LG

Non-Iterative Knowledge Fusion in Deep Convolutional Neural Networks

S.P. Kapitsa Research Institute of Technology (Technological Research Institute) of Ulyanovsk State University（乌里扬诺夫斯克国立大学S.P.卡皮察技术研究所（技术研究所））；Ulyanovsk State Technical University（乌里扬诺夫斯克国立技术大学）；Kotel’nikov Institute of Radio Engineering and Electronics of Russian Academy of Sciences (Ulyanovsk branch)（俄罗斯科学院科捷利尼科夫无线电工程与电子研究所（乌里扬诺夫斯克分支））

Incorporation of a new knowledge into neural networks with simultaneous preservation of the previous one is known to be a nontrivial problem. This problem becomes even more complex when new knowledge is contained not in new training examples, but inside the parameters (connection weights) of another neural network. Here we propose and test two methods allowing combining the knowledge contained in separate networks. One method is based on a simple operation of summation of weights of constituent neural networks. Another method assumes incorporation of a new knowledge by modification of weights …

2018-09-25cs.LGstat.ML