An Extensive Study and Review of Privacy Preservation Models for the Multi-Institutional Data

The deep learning models hold considerable potential for clinical applications, but there are many challenges to successfully training deep learning models. Large-scale data collection is required, which is frequently only possible through multi-institutional cooperation. Building large central repositories is one strategy for multi-institution studies. However, this is hampered by issues regarding data sharing, including patient privacy, data de-identification, regulation, intellectual property, and data storage. These difficulties have lessened the impracticality of central data storage. In this survey, we will look at 24 research publications that concentrate on machine learning approaches linked to privacy preservation techniques for multi-institutional data, highlighting the multiple shortcomings of the existing methodologies. Researching different approaches will be made simpler in this case based on a number of factors, such as performance measures, year of publication and journals, achievements of the strategies in numerical assessments, and other factors. A technique analysis that considers the benefits and drawbacks of the strategies is additionally provided. The article also looks at some potential areas for future research as well as the challenges associated with increasing the accuracy of privacy protection techniques. The comparative evaluation of the approaches offers a thorough justification for the research’s purpose.

Attacks on Anonymization-Based Privacy-Preserving: A Survey for Data Mining and Data Publishing

Data mining is the extraction of vast interesting patterns or knowledge from huge amount of data. The initial idea of privacy-preserving data mining PPDM was to extend traditional data mining techniques to work with the data modified to mask sensitive information. The key issues were how to modify the data and how to recover the data mining result from the modified data. Privacy-preserving data mining considers the problem of running data mining algorithms on confidential data that is not supposed to be revealed even to the party running the algorithm. In contrast, privacy-preserving data publishing (PPDP) may not necessarily be tied to a specific data mining task, and the data mining task may be unknown at the time of data publishing. PPDP studies how to transform raw data into a version that is immunized against privacy attacks but that still supports effective data mining tasks. Privacy-preserving for both data mining (PPDM) and data publishing (PPDP) has become increasingly popular because it allows sharing of privacy sensitive data for analysis purposes. One well studied approach is the k-anonymity model [1] which in turn led to other models such as confidence bounding, l-diversity, t-closeness, (α,k)-anonymity, etc. In particular, all known mechanisms try to minimize information loss and such an attempt provides a loophole for attacks. The aim of this paper is to present a survey for most of the common attacks techniques for anonymization-based PPDM & PPDP and explain their effects on Data Privacy.

Slicing-Based Enhanced Method for Privacy-Preserving in Publishing Big Data

Publishing big data and making it accessible to researchers is important for knowledge building as it helps in applying highly efficient methods to plan,conduct,and assess scientific research.However,publishing and processing big data poses a privacy concern related to protecting individuals’sensitive information while maintaining the usability of the published data.Several anonymization methods,such as slicing and merging,have been designed as solutions to the privacy concerns for publishing big data.However,the major drawback of merging and slicing is the random permutation procedure,which does not always guarantee complete protection against attribute or membership disclosure.Moreover,merging procedures may generatemany fake tuples,leading to a loss of data utility and subsequent erroneous knowledge extraction.This study therefore proposes a slicingbased enhanced method for privacy-preserving big data publishing while maintaining the data utility.In particular,the proposed method distributes the data into horizontal and vertical partitions.The lower and upper protection levels are then used to identify the unique and identical attributes’values.The unique and identical attributes are swapped to ensure the published big data is protected from disclosure risks.The outcome of the experiments demonstrates that the proposed method could maintain data utility and provide stronger privacy preservation.

A Differential Privacy Based (k-Ψ)-Anonymity Method for Trajectory Data Publishing

In recent years,mobile Internet technology and location based services have wide application.Application providers and users have accumulated huge amount of trajectory data.While publishing and analyzing user trajectory data have brought great convenience for people,the disclosure risks of user privacy caused by the trajectory data publishing are also becoming more and more prominent.Traditional k-anonymous trajectory data publishing technologies cannot effectively protect user privacy against attackers with strong background knowledge.For privacy preserving trajectory data publishing,we propose a differential privacy based(k-Ψ)-anonymity method to defend against re-identification and probabilistic inference attack.The proposed method is divided into two phases:in the first phase,a dummy-based(k-Ψ)-anonymous trajectory data publishing algorithm is given,which improves(k-δ)-anonymity by considering changes of thresholdδon different road segments and constructing an adaptive threshold setΨthat takes into account road network information.In the second phase,Laplace noise regarding distance of anonymous locations under differential privacy is used for trajectory perturbation of the anonymous trajectory dataset outputted by the first phase.Experiments on real road network dataset are performed and the results show that the proposed method improves the trajectory indistinguishability and achieves good data utility in condition of preserving user privacy.

Research of Privacy Preservation Method Based on Data Coloring

In the cloud computing environment, outsourcing service mode of data storage causes the security problem, the reliability of data cannot be guaranteed, and the privacy preservation problem has aroused wide concern. In order to solve the problem of inefficiency and high-complexity caused by traditional privacy preservation methods such as data encryption and access control technology, a privacy preservation method based on data coloring is proposed. The data coloring model is established and the coloring mechanism is adopted to deal with the sensitive data of numerical attributes, and the cloud model similarity measurement based on arithmetic average least-approximability is adopted to authenticate the ownership of privacy data. On the premise of high availability of data, the method strengthens the security of the privacy information. Then, the performance, validity and the parameter errors of the algorithm are quantitatively analyzed by the experiments using the UCI dataset. Under the same conditions of privacy preservation requirements, the proposed method can track privacy leakage efficiently and reduce privacy leakage risks. Compared with the k-anonymity approach, the proposed method enhances the computational time efficiency by 18.5%.

Attacks and Countermeasures in Social Network Data Publishing

With the increasing prevalence of social networks, more and more social network data are published for many applications, such as social network analysis and data mining. However, this brings privacy problems. For example, adversaries can get sensitive information of some individuals easily with little background knowledge. How to publish social network data for analysis purpose while preserving the privacy of individuals has raised many concerns. Many algorithms have been proposed to address this issue. In this paper, we discuss this privacy problem from two aspects： attack models and countermeasures. We analyse privacy conceres, model the background knowledge that adversary may utilize and review the recently developed attack models. We then survey the state-of-the-art privacy preserving methods in two categories： anonymization methods and differential privacy methods. We also provide research directions in this area.

云-边融合的可验证隐私保护跨域联邦学习方案

联邦学习技术的飞速发展促进不同终端用户数据协同训练梯度模型,其显著特征是训练数据集不离开本地设备,只有梯度模型在本地进行更新并共享,使边缘服务器生成全局梯度模型。然而,本地设备间的异构性会影响训练性能,且共享梯度模型更新具有隐私泄密与恶意篡改威胁。提出云-边融合的可验证隐私保护跨域联邦学习方案。在方案中,终端用户利用单掩码盲化技术保护数据隐私,利用基于向量内积的签名算法产生梯度模型的签名,边缘服务器通过盲化技术聚合隐私数据并产生去盲化聚合签名,确保全局梯度模型更新与共享过程的不可篡改性。采用多区域权重转发技术解决异构网络中设备计算资源与通信开销受限的问题。实验结果表明,该方案能够安全高效地部署在异构网络中,并在MNIST、SVHN、CIFAR-10和CIFAR-1004个基准数据集上进行系统实验仿真,与经典联邦学习方案相比,在精度相当的情况下,本文方案梯度模型收敛速度平均提高了21.6%。

混洗差分隐私保护的度分布直方图发布算法

当前,基于中心化或本地差分隐私的图数据度分布直方图发布算法无法有效平衡发布数据的隐私保护程度及其可用性,且不能有效保护用户的身份隐私。针对该问题,在编码-混洗-分析框架下提出一种混洗差分隐私保护的度分布直方图发布算法。首先,设计混洗差分隐私图数据度分布直方图隐私保护框架,采取交互式用户分组、混洗器及方波本地加噪扰动机制降低编码器对分布式用户本地差分隐私加噪的噪声影响,并利用极大似然估计在分析器端对加噪后的度分布直方图进行数据矫正,从而提高数据效用;其次,提出具体的分布式用户分组、混洗差分隐私加噪和数据矫正算法,并证明其满足(ε,σ)-混洗差分隐私。实验和对比结果表明,所提算法能保护分布式用户隐私,在L_(1)距离、H距离和MSE多个指标度量下的数据效用比已有算法提升了26%以上,且具有较低的时间开销和稳定的数据效用表现,适用不同规模的图数据度分布直方图发布共享应用。

位置轨迹相关性差分隐私保护技术研究与进展

随着移动互联网、智能终端设备和GPS定位技术的普及应用,产生了大量轨迹数据以应用于基于位置的服务.然而,具有时空相关性的行动轨迹可以体现或泄露单用户的个人信息或多用户之间的某些社会关系信息,进一步导致严重的隐私泄露.这些位置轨迹数据的共享和发布离不开隐私保护技术的支持,而大多数隐私保护模型的安全性是基于一定的背景知识,若背景知识已被攻击者掌握,则无法提供完善的隐私保护.差分隐私技术有效弥补这一缺陷,并广泛应用于位置轨迹数据相关性隐私保护领域中.本文首先介绍差分隐私、全局敏感度、噪声机制以及组合性质等相关概念;其次系统地对基于差分隐私的位置轨迹相关性隐私保护技术进行了研究与分析,进一步地详细阐述了差分隐私模型下单条轨迹内相关性保护、两条不同轨迹之间相关性保护以及多条不同轨迹之间相关性保护在时间、空间以及时空方面的隐私保护方法;最后,在对现有方法对比分析的基础上,提出了位置轨迹相关性隐私保护未来的重点研究发展方向.

基于哈夫曼的k-匿名模型隐私保护数据压缩方案

k-匿名模型作为常用的数据匿名技术,广泛应用于数据发布阶段的隐私保护。随着大数据时代的快速发展,海量数据的产生给数据存储带来了新的挑战。然而,存储器的成本较高且存储空间有限,通过硬件升级来无限制地扩充存储空间并不可行。为此,使用数据压缩技术可以减少存储成本和通信开销。为减少数据发布阶段使用匿名技术产生的数据的存储空间,提出了k-匿名模型隐私保护数据压缩方案。对于k-匿名模型的原始数据,按照设定的规则及原始数据同匿名数据之间的预设泛化层次关系计算两者的差值,并根据差值数据具有的频率特性对差值进行哈夫曼编码压缩。通过存储差值可以间接获得原始数据,从而减少原始数据的存储空间。对于k-匿名模型的匿名数据,根据模型的泛化规则或预设泛化层次关系,匿名数据通常具有较高的重复性,且设定的k值越大,匿名数据的泛化程度越高、重复性越强。对匿名数据设计实现哈夫曼编码压缩,减少匿名数据的存储空间。实验结果表明,所提方案能够显著降低k-匿名模型的原始数据及匿名数据的压缩率。在使用的5个k-匿名模型及不同k值的设定情况下,与Windows 11的zip工具相比,所提方案的原始数据压缩率和匿名数据压缩率平均降低了72.2%、64.2%。

基于用户同意的隐私保护协议形式化描述与验证

将用户同意与访问控制相结合是解决隐私保护的主要方法之一.然而,现有的隐私保护访问控制方法仅从数据控制者的角度,不考虑个人对访问决策的参与,无法满足自主可控的需求.为了解决这个问题,本文提出了一种基于用户同意的隐私保护访问控制协议,将用户同意转化为一种同意权限,形成一种同意加授权的双重访问控制机制.本文给出协议的语法、语义及安全性定义和分析,并采用模型检测的方法对协议应满足的性质进行验证,最终证明本文的设计可以从访问控制的角度满足个人信息保护法规的要求.

ChatGPT安全威胁研究

随着深度学习技术与自然语言处理技术的快速发展,以ChatGPT为代表的大型语言模型应运而生,然而其在诸多领域展现出令人惊讶的能力的同时,也暴露出诸多安全威胁,这引发了学术界与产业界的担忧.首先,介绍了ChatGPT及其系列模型的发展历程、工作模式与训练方式;然后,从用户和模型2个层面总结并分析了当前ChatGPT可能遇到的各类安全问题,并提出应对思路与方案;最后,对ChatGPT以及大型语言模型领域未来如何安全可信地发展进行了展望.

基于神经网络模型的成员推理防御算法

【目的】针对机器学习模型在训练过程中可能泄露训练数据隐私,为成员推理攻击所利用,进而窃取用户敏感信息的问题,提出了一种基于神经网络的期望均衡优化算法(EEO).【方法】采用对抗训练并优化的策略,分为内外两层循环来实现:内层循环假设一个足够强大的对手,其目标为最大化攻击模型期望;外层循环有针对性地进行防御训练,其目标为最大化目标模型期望。利用小批量梯度下降法使内外两层循环的损失值都达到最小,从而既保证模型精度,又降低对手成员推理的能力。【结果】采用3个有代表性的图像数据集MNIST、FASHION、Face,将EEO应用于优化后的神经网络模型进行成员推理攻击实验,3个数据集的测试精度分别损失了2.2%、4.7%和3.7%,而攻击模型的精度分别下降了14.6%、16.5%和13.9%,并且已接近50%,即随机猜测。【结论】实验结果表明该算法较好地兼顾了模型的高可用性与高隐私性,尽管仍会不可避免地产生隐私泄露,但训练出的神经网络模型对成员推理攻击有很强的防御效果,且对目标模型的影响可以忽略。

隐私保护数据发布中身份保持的匿名方法

在隐私保护的数据发布研究中,目前的方法通常都是先删除身份标识属性,然后对准标识属性进行匿名处理.分析了单一个体对应多个记录的情况,提出了一种保持身份标识属性的匿名方法,它在保持隐私的同时进一步提高了信息有效性.采用概化和有损连接两种实现方式.实验结果表明,该方法提高了信息有效性,具有很好的实用性.

基于轨迹频率抑制的轨迹隐私保护方法

移动终端和定位技术的快速发展带来了轨迹大数据.研究者通过挖掘和分析发布的轨迹数据集,可获得一些有价值的信息.攻击者也可利用所掌握的知识对发布的轨迹数据集进行推理分析,以较高的概率推断出用户的隐私信息.轨迹抑制是一类实现隐私保护的重要方法,然而轨迹抑制的点数越多会造成数据效用越低.因此,在满足用户隐私需求的情况下,如何选择合理的抑制点来提高匿名处理后的数据效用是数据发布中要解决的重要问题.针对以上问题,文中提出两种基于轨迹频率的方案对轨迹数据进行匿名处理.第一种方案是根据情况抑制整条有问题的轨迹数据或向有问题的轨迹数据集中添加假数据;第二种方案是采用特定的轨迹局部抑制法对数据进行抑制处理.实验表明相对于已有方案,在满足同等隐私需求的情况下,文中方案处理后的数据效用提升了近30%.

基于聚类杂交的隐私保护轨迹数据发布算法

传统关于轨迹数据发布的隐私保护研究大多采用聚类技术,其相关算法只关注每条轨迹的隐私保护,忽视对轨迹聚类组特征的保护.通过理论分析和实验验证发现,对采用聚类发布技术产生的轨迹数据进行二次聚类,可得到原始轨迹数据在发布之前的聚类组特征,从而可能导致隐私泄露.为了有效预防二次聚类攻击,提出一种(k,δ,Δ)-匿名模型和基于该模型的聚类杂交隐私保护轨迹数据发布算法CH-TDP,算法CH-TDP对采用(k,δ)-匿名模型及相关算法处理得到的聚类分组先进行组间杂交,而后再进行组内扰乱,其目标在防止出现二次聚类攻击的前提下,保证发布轨迹数据的质量不低于阈值Δ.实验对算法CH-TDP的可行性及有效性与同类算法进行比较分析,结果表明算法CH-TDP是有效可行的.

一种考虑属性权重的隐私保护数据发布方法

k-匿名模型是数据发布领域用于对原始待发布数据集进行匿名处理以阻止链接攻击的有效方法之一,但已有的k-匿名及其改进模型没有考虑不同应用领域对匿名发布表数据质量需求不同的问题.在特定应用领域不同准码属性对基于匿名发布表的数据分析任务效用的贡献程度是不同的,若没有根据发布表用途的差异区别处理各准码属性的泛化过程,将会导致泛化后匿名发布表数据效用较差、无法满足具体数据分析任务的需要.在分析不同应用领域数据分析任务特点的基础上,首先通过修正基本ODP目录系统建立适用于特定问题领域的概念泛化结构;然后在泛化过程中为不同准码属性的泛化路径设置权重以反映具体数据分析任务对各准码属性的不同要求;最后设计一种考虑属性权重的数据匿名发布算法WAK(QI weight-aware k-anonymity),这是一种灵活地保持匿名发布表数据效用的隐私保护问题解决方案.示例分析和实验结果表明,利用该方案求解的泛化匿名发布表在达到指定隐私保护目标的同时,能够保持较高的数据效用,满足具体应用领域特定数据分析任务对数据质量的要求.

社会网络数据发布隐私保护技术综述

对社会网络隐私保护的研究现状与进展进行了阐述.首先介绍了社会网络隐私保护问题的研究背景,进而从社会网络中的隐私、攻击者背景知识、社会网络数据隐私保护技术、数据可用性与实验测评等方面对当前研究工作进行了细致的分类归纳和分析,指出了当前社会网络隐私保护的不足以及不同隐私保护技术间的对比和优缺点,并对未来需要深入研究的方向进行了展望.对社会网络数据隐私保护研究的主流方法和前沿进展进行了概括、比较和分析.

位置大数据服务中基于差分隐私的数据发布技术

应对多组合复杂攻击及前景知识攻击,提出一种新的基于差分隐私保护机制的位置大数据发布模型,创新设计可用性评估反馈机制模块,引入时间变量动态地针对敏感属性以及身份识别等分析模型的服务质量,能在位置大数据与非位置大数据相结合、用户背景知识不确定等情况下保护用户的位置隐私。仿真实验基于多种空间索引技术验证了新发布模型能够在指定的私密性条件下,为位置查询服务发布具有更高准确率的匿名数据。

面向表数据发布隐私保护的贪心聚类匿名方法

为了防范隐私泄露,表数据一般需要匿名处理后发布.现有匿名方案较少分类考察准标识属性概化,并缺少同时考虑信息损失量和时间效率的最优化.利用贪心法和聚类划分的思想,提出一种贪心聚类匿名方法:分类概化准标识属性,并分别度量其信息损失,有利于减小并合理评价信息损失.对元组间距离和元组与等价类距离,建立与最小合并概化信息损失值正相关的距离定义,聚类过程始终选取具有最小距离值的元组添加,从而保证信息损失总量趋于最小.按照k值控制逐一聚类,实现等价类均衡划分,减少了距离计算总量,节省了运行时间.实验结果表明,该方法在减少信息损失和运行时间方面是有效的.