在培训敏感和个人数据时,机器学习模型的隐私风险是主要问题。我们讨论数据隐私与可信赖的机器学习的其余目标之间的权衡(尤其是公平,鲁棒性和解释性)。
translated by 谷歌翻译
从公共机器学习(ML)模型中泄漏数据是一个越来越重要的领域,因为ML的商业和政府应用可以利用多个数据源,可能包括用户和客户的敏感数据。我们对几个方面的当代进步进行了全面的调查,涵盖了非自愿数据泄漏,这对ML模型很自然,潜在的恶毒泄漏是由隐私攻击引起的,以及目前可用的防御机制。我们专注于推理时间泄漏,这是公开可用模型的最可能场景。我们首先在不同的数据,任务和模型体系结构的背景下讨论什么是泄漏。然后,我们提出了跨非自愿和恶意泄漏的分类法,可用的防御措施,然后进行当前可用的评估指标和应用。我们以杰出的挑战和开放性的问题结束,概述了一些有希望的未来研究方向。
translated by 谷歌翻译
A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well understood and demonstrated attacks often rely on strong and unrealistic assumptions such as full knowledge of training environments even in supposedly black-box threat scenarios. To improve understanding of distribution inference risks, we develop a new black-box attack that even outperforms the best known white-box attack in most settings. Using this new attack, we evaluate distribution inference risk while relaxing a variety of assumptions about the adversary's knowledge under black-box access, like known model architectures and label-only access. Finally, we evaluate the effectiveness of previously proposed defenses and introduce new defenses. We find that although noise-based defenses appear to be ineffective, a simple re-sampling defense can be highly effective. Code is available at https://github.com/iamgroot42/dissecting_distribution_inference
translated by 谷歌翻译
Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, , about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of in order to get acceptable utility of the model, with little understanding of the impact of such choices on meaningful privacy. Moreover, in scenarios where iterative learning procedures are used, differential privacy variants that offer tighter analyses are used which appear to reduce the needed privacy budget but present poorly understood trade-offs between privacy and utility. In this paper, we quantify the impact of these choices on privacy in experiments with logistic regression and neural network models. Our main finding is that there is a huge gap between the upper bounds on privacy loss that can be guaranteed, even with advanced mechanisms, and the effective privacy loss that can be measured using current inference attacks. Current mechanisms for differentially private machine learning rarely offer acceptable utility-privacy trade-offs with guarantees for complex learning tasks: settings that provide limited accuracy loss provide meaningless privacy guarantees, and settings that provide strong privacy guarantees result in useless models.
translated by 谷歌翻译
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to reconstruction attacks. Inspired by the success of games (i.e., probabilistic experiments) to study security properties in cryptography, some authors describe privacy inference risks in machine learning using a similar game-based style. However, adversary capabilities and goals are often stated in subtly different ways from one presentation to the other, which makes it hard to relate and compose results. In this paper, we present a game-based framework to systematize the body of knowledge on privacy inference risks in machine learning.
translated by 谷歌翻译
Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to distinguish between data points that were part of the model's training set and any other data points from the same distribution. This is known as the tracing (and also membership inference) attack. In this paper, we focus on such attacks against black-box models, where the adversary can only observe the output of the model, but not its parameters. This is the current setting of machine learning as a service in the Internet.We introduce a privacy mechanism to train machine learning models that provably achieve membership privacy: the model's predictions on its training data are indistinguishable from its predictions on other data points from the same distribution. We design a strategic mechanism where the privacy mechanism anticipates the membership inference attacks. The objective is to train a model such that not only does it have the minimum prediction error (high utility), but also it is the most robust model against its corresponding strongest inference attack (high privacy). We formalize this as a min-max game optimization problem, and design an adversarial training algorithm that minimizes the classification loss of the model as well as the maximum gain of the membership inference attack against it. This strategy, which guarantees membership privacy (as prediction indistinguishability), acts also as a strong regularizer and significantly generalizes the model.We evaluate our privacy mechanism on deep neural networks using different benchmark datasets. We show that our min-max strategy can mitigate the risk of membership inference attacks (close to the random guess) with a negligible cost in terms of the classification error.
translated by 谷歌翻译
Speech-centric machine learning systems have revolutionized many leading domains ranging from transportation and healthcare to education and defense, profoundly changing how people live, work, and interact with each other. However, recent studies have demonstrated that many speech-centric ML systems may need to be considered more trustworthy for broader deployment. Specifically, concerns over privacy breaches, discriminating performance, and vulnerability to adversarial attacks have all been discovered in ML research fields. In order to address the above challenges and risks, a significant number of efforts have been made to ensure these ML systems are trustworthy, especially private, safe, and fair. In this paper, we conduct the first comprehensive survey on speech-centric trustworthy ML topics related to privacy, safety, and fairness. In addition to serving as a summary report for the research community, we point out several promising future research directions to inspire the researchers who wish to explore further in this area.
translated by 谷歌翻译
机器学习(ML)模型已广泛应用于各种应用,包括图像分类,文本生成,音频识别和图形数据分析。然而,最近的研究表明,ML模型容易受到隶属推导攻击(MIS),其目的是推断数据记录是否用于训练目标模型。 ML模型上的MIA可以直接导致隐私违规行为。例如,通过确定已经用于训练与某种疾病相关的模型的临床记录,攻击者可以推断临床记录的所有者具有很大的机会。近年来,MIS已被证明对各种ML模型有效,例如,分类模型和生成模型。同时,已经提出了许多防御方法来减轻米西亚。虽然ML模型上的MIAS形成了一个新的新兴和快速增长的研究区,但还没有对这一主题进行系统的调查。在本文中,我们对会员推论和防御进行了第一个全面调查。我们根据其特征提供攻击和防御的分类管理,并讨论其优点和缺点。根据本次调查中确定的限制和差距,我们指出了几个未来的未来研究方向,以激发希望遵循该地区的研究人员。这项调查不仅是研究社区的参考,而且还为该研究领域之外的研究人员带来了清晰的照片。为了进一步促进研究人员,我们创建了一个在线资源存储库,并与未来的相关作品继续更新。感兴趣的读者可以在https://github.com/hongshenghu/membership-inference-machine-learning-literature找到存储库。
translated by 谷歌翻译
近年来,关于如何在公平限制下学习机器学习模型的越来越多的工作,通常在某些敏感属性方面表达。在这项工作中,我们考虑了对手对目标模型具有黑箱访问的设置,并表明对手可以利用有关该模型公平性的信息,以增强他对训练数据敏感属性的重建。更确切地说,我们提出了一种通用的重建校正方法,该方法将其作为对手进行的初始猜测,并纠正它以符合某些用户定义的约束(例如公平信息),同时最大程度地减少了对手猜测的变化。提出的方法对目标模型的类型,公平感知的学习方法以及对手的辅助知识不可知。为了评估我们的方法的适用性,我们对两种最先进的公平学习方法进行了彻底的实验评估,使用四个具有广泛公差的不同公平指标以及三个不同大小和敏感属性的数据集。实验结果证明了提出的方法改善训练集敏感属性的重建的有效性。
translated by 谷歌翻译
在其培训集中,给定训练有素的模型泄漏了多少培训模型泄露?会员资格推理攻击用作审计工具,以量化模型在其训练集中泄漏的私人信息。会员推理攻击受到不同不确定性的影响,即攻击者必须解决培训数据,培训算法和底层数据分布。因此,攻击成功率,在文献中的许多攻击,不要精确地捕获模型的信息泄漏关于他们的数据,因为它们还反映了攻击算法具有的其他不确定性。在本文中,我们解释了隐含的假设以及使用假设检测框架在现有工作中进行的简化。我们还从框架中获得了新的攻击算法,可以实现高AUC分数,同时还突出显示影响其性能的不同因素。我们的算法捕获模型中隐私损失的非常精确的近似,并且可以用作在机器学习模型中执行准确和了解的隐私风险的工具。我们对各种机器学习任务和基准数据集的攻击策略提供了彻底的实证评估。
translated by 谷歌翻译
随着全球人口越来越多的人口驱动世界各地的快速城市化,有很大的需要蓄意审议值得生活的未来。特别是,随着现代智能城市拥抱越来越多的数据驱动的人工智能服务,值得记住技术可以促进繁荣,福祉,城市居住能力或社会正义,而是只有当它具有正确的模拟补充时(例如竭尽全力,成熟机构,负责任治理);这些智能城市的最终目标是促进和提高人类福利和社会繁荣。研究人员表明,各种技术商业模式和特征实际上可以有助于极端主义,极化,错误信息和互联网成瘾等社会问题。鉴于这些观察,解决了确保了诸如未来城市技术基岩的安全,安全和可解释性的哲学和道德问题,以为未来城市的技术基岩具有至关重要的。在全球范围内,有能够更加人性化和以人为本的技术。在本文中,我们分析和探索了在人以人为本的应用中成功部署AI的安全,鲁棒性,可解释性和道德(数据和算法)挑战的关键挑战,特别强调这些概念/挑战的融合。我们对这些关键挑战提供了对现有文献的详细审查,并分析了这些挑战中的一个可能导致他人的挑战方式或帮助解决其他挑战。本文还建议了这些域的当前限制,陷阱和未来研究方向,以及如何填补当前的空白并导致更好的解决方案。我们认为,这种严谨的分析将为域名的未来研究提供基准。
translated by 谷歌翻译
We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model, determine if the record was in the model's training dataset. To perform membership inference against a target model, we make adversarial use of machine learning and train our own inference model to recognize differences in the target model's predictions on the inputs that it trained on versus the inputs that it did not train on.We empirically evaluate our inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon. Using realistic datasets and classification tasks, including a hospital discharge dataset whose membership is sensitive from the privacy perspective, we show that these models can be vulnerable to membership inference attacks. We then investigate the factors that influence this leakage and evaluate mitigation strategies.
translated by 谷歌翻译
联邦学习的出现在维持隐私的同时,促进了机器学习模型之间的大规模数据交换。尽管历史悠久,但联邦学习正在迅速发展,以使更广泛的使用更加实用。该领域中最重要的进步之一是将转移学习纳入联邦学习,这克服了主要联合学习的基本限制,尤其是在安全方面。本章从安全的角度进行了有关联合和转移学习的交集的全面调查。这项研究的主要目标是发现可能损害使用联合和转移学习的系统的隐私和性能的潜在脆弱性和防御机制。
translated by 谷歌翻译
模型可以公开有关其培训数据的敏感信息。在属性推理攻击中,对手对某些培训记录有部分知识,并访问了对这些记录进行培训的模型,并渗透了这些记录敏感功能的未知值。我们研究了一种属性推理的细粒变体,我们称为\ emph {敏感值推理},其中对手的目标是高度置信度识别一些来自候选人集的记录,其中未知属性具有特定的敏感值。我们将属性推断与捕获培训分布统计数据的数据插补进行明确比较,该数据在对对手可用的培训数据的各种假设下进行了比较。我们的主要结论是:(1)以前的属性推理方法并没有比对手可以推断出有关训练数据的训练数据的更多信息,而无需访问训练的模型,而是对培训所需的基础分布相同的知识属性推理攻击; (2)Black-Box属性推理攻击很少学习没有模型的任何东西;但是(3)我们在论文中介绍和评估的白框攻击可以可靠地识别一些具有敏感值属性的记录,而这些记录在不访问模型的情况下无法预测。此外,我们表明提出的防御措施,例如私人培训和从培训中删除脆弱记录不会减轻这种隐私风险。我们的实验代码可在\ url {https://github.com/bargavj/evaluatingdpml}上获得。
translated by 谷歌翻译
隐私敏感数据的培训机器学习模型已成为一种流行的练习,在不断扩大的田野中推动创新。这已经向新攻击打开了门,这可能会产生严重的隐私含义。一个这样的攻击,会员推导攻击(MIA),暴露了特定数据点是否用于训练模型。一种越来越多的文献使用差异的私人(DP)训练算法作为反对这种攻击的辩护。但是,这些作品根据限制假设评估防御,即所有培训集以及非成员的所有成员都是独立的并相同分布的。这种假设没有在文献中的许多真实用例中占据。由此激励,我们评估隶属于样本之间的统计依赖性,并解释为什么DP不提供有意义的保护(在这种更常规的情况下,培训集尺寸$ N $的隐私参数$ \ epsilon $ scales)。我们使用从现实世界数据构建的培训集进行了一系列实证评估,其中包括示出样品之间的不同类型依赖性的培训集。我们的结果表明,培训集依赖关系可能会严重增加MIS的性能,因此假设数据样本在统计上独立,可以显着低估均撒的性能。
translated by 谷歌翻译
联合学习中的隐私(FL)以两种不同的粒度进行了研究:项目级,该项目级别保护单个数据点和用户级别,该数据点保护联邦中的每个用户(参与者)。几乎所有的私人文献都致力于研究这两种粒度的隐私攻击和防御。最近,主题级隐私已成为一种替代性隐私粒度,以保护个人(数据主体)的隐私(数据主题),其数据分布在跨索洛FL设置中的多个(组织)用户。对手可能有兴趣通过攻击受过训练的模型来恢复有关这些人(又称emph {data主体})的私人信息。对这些模式的系统研究需要对联邦的完全控制,而实际数据集是不可能的。我们设计了一个模拟器,用于生成各种合成联邦配置,使我们能够研究数据的属性,模型设计和培训以及联合会本身如何影响主题隐私风险。我们提出了\ emph {主题成员推理}的三个攻击,并检查影响攻击功效的联邦中所有因素之间的相互作用。我们还研究了差异隐私在减轻这种威胁方面的有效性。我们的收获概括到像女权主义者这样的现实世界数据集中,对我们的发现赋予了信任。
translated by 谷歌翻译
会员推理攻击是机器学习模型中最简单的隐私泄漏形式之一:给定数据点和模型,确定该点是否用于培训模型。当查询其培训数据时,现有会员推理攻击利用模型的异常置信度。如果对手访问模型的预测标签,则不会申请这些攻击,而不会置信度。在本文中,我们介绍了仅限标签的会员资格推理攻击。我们的攻击而不是依赖置信分数,而是评估模型预测标签在扰动下的稳健性,以获得细粒度的隶属信号。这些扰动包括常见的数据增强或对抗例。我们经验表明,我们的标签占会员推理攻击与先前攻击相符,以便需要访问模型信心。我们进一步证明,仅限标签攻击违反了(隐含或明确)依赖于我们呼叫信心屏蔽的现象的员工推论攻击的多种防御。这些防御修改了模型的置信度分数以挫败攻击,但留下模型的预测标签不变。我们的标签攻击展示了置信性掩蔽不是抵御会员推理的可行的防御策略。最后,我们调查唯一的案例标签攻击,该攻击推断为少量异常值数据点。我们显示仅标签攻击也匹配此设置中基于置信的攻击。我们发现具有差异隐私和(强)L2正则化的培训模型是唯一已知的防御策略,成功地防止所有攻击。即使差异隐私预算太高而无法提供有意义的可证明担保,这仍然存在。
translated by 谷歌翻译
制药行业可以更好地利用其数据资产来通过协作机器学习平台虚拟化药物发现。另一方面,由于参与者的培训数据的意外泄漏,存在不可忽略的风险,因此,对于这样的平台,必须安全和隐私权。本文介绍了在药物发现的临床前阶段进行协作建模的隐私风险评估,以加快有前途的候选药物的选择。在最新推理攻击的简短分类法之后,我们采用并定制了几种基础情况。最后,我们用一些相关的隐私保护技术来描述和实验,以减轻此类攻击。
translated by 谷歌翻译
Motivated by mitigating potentially harmful impacts of technologies, the AI community has formulated and accepted mathematical definitions for certain pillars of accountability: e.g. privacy, fairness, and model transparency. Yet, we argue this is fundamentally misguided because these definitions are imperfect, siloed constructions of the human values they hope to proxy, while giving the guise that those values are sufficiently embedded in our technologies. Under popularized methods, tensions arise when practitioners attempt to achieve each pillar of fairness, privacy, and transparency in isolation or simultaneously. In this position paper, we push for redirection. We argue that the AI community needs to consider all the consequences of choosing certain formulations of these pillars -- not just the technical incompatibilities, but also the effects within the context of deployment. We point towards sociotechnical research for frameworks for the latter, but push for broader efforts into implementing these in practice.
translated by 谷歌翻译
员额推理攻击允许对训练的机器学习模型进行对手以预测模型的训练数据集中包含特定示例。目前使用平均案例的“精度”度量来评估这些攻击,该攻击未能表征攻击是否可以自信地识别培训集的任何成员。我们认为,应该通过计算其低(例如<0.1%)假阳性率来计算攻击来评估攻击,并在以这种方式评估时发现大多数事先攻击差。为了解决这一问题,我们开发了一个仔细结合文献中多种想法的似然比攻击(Lira)。我们的攻击是低于虚假阳性率的10倍,并且在攻击现有度量的情况下也严格占主导地位。
translated by 谷歌翻译