尽管早期的经验证据支持了学到的索引结构的案例,因为它们具有有利的平均案例表现,但对其最差的表现知之甚少。相比之下,已知经典结构可以实现最佳的最坏情况行为。这项工作评估了在存在对抗工作量的情况下学习指数结构的鲁棒性。为了模拟对抗性工作负载,我们对线性回归模型进行了数据中毒攻击,该模型操纵了训练学习的索引模型的累积分布函数(CDF)。攻击通过将一组中毒键注入训练数据集,从而恶化了基础ML模型的拟合度,从而导致模型的预测误差增加,从而减少了学习指数结构的整体性能。我们评估了各种回归方法的性能和学习指数实现Alex和PGM索引。我们表明,在对中毒与非毒品数据集进行评估时,学到的指数结构可能会遭受高达20%的显着性能恶化。
translated by 谷歌翻译
A learned system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or processes, much like microarchitectural resources such as caches, potentially giving rise to highly-realistic attacker models. However, compared to attacks on other ML-based systems, attackers face a level of indirection as they cannot interact directly with the learned model. Additionally, the difference between the attack surface of learned and non-learned versions of the same system is often subtle. These factors obfuscate the de-facto risks that the incorporation of ML carries. We analyze the root causes of potentially-increased attack surface in learned systems and develop a framework for identifying vulnerabilities that stem from the use of ML. We apply our framework to a broad set of learned systems under active development. To empirically validate the many vulnerabilities surfaced by our framework, we choose 3 of them and implement and evaluate exploits against prominent learned-system instances. We show that the use of ML caused leakage of past queries in a database, enabled a poisoning attack that causes exponential memory blowup in an index structure and crashes it in seconds, and enabled index users to snoop on each others' key distributions by timing queries over their own keys. We find that adversarial ML is a universal threat against learned systems, point to open research gaps in our understanding of learned-systems security, and conclude by discussing mitigations, while noting that data leakage is inherent in systems whose learned component is shared between multiple parties.
translated by 谷歌翻译
Learning-based pattern classifiers, including deep networks, have shown impressive performance in several application domains, ranging from computer vision to cybersecurity. However, it has also been shown that adversarial input perturbations carefully crafted either at training or at test time can easily subvert their predictions. The vulnerability of machine learning to such wild patterns (also referred to as adversarial examples), along with the design of suitable countermeasures, have been investigated in the research field of adversarial machine learning. In this work, we provide a thorough overview of the evolution of this research area over the last ten years and beyond, starting from pioneering, earlier work on the security of non-deep learning algorithms up to more recent work aimed to understand the security properties of deep learning algorithms, in the context of computer vision and cybersecurity tasks. We report interesting connections between these apparently-different lines of work, highlighting common misconceptions related to the security evaluation of machine-learning algorithms. We review the main threat models and attacks defined to this end, and discuss the main limitations of current work, along with the corresponding future challenges towards the design of more secure learning algorithms.
translated by 谷歌翻译
数据中毒是对机器学习和数据驱动技术的最相关的安全威胁之一。由于许多应用程序依赖于不受信任的培训数据,因此攻击者可以轻松地将恶意样本轻松地将其注入训练数据集,以降低机器学习模型的性能。正如最近的工作所示,这种拒绝服务(DOS)数据中毒攻击非常有效。为了减轻这种威胁,我们提出了一种检测DOS中毒实例的新方法。与相关工作相比,我们偏离基于聚类和异常检测的方法,这通常遭受维度的诅咒和任意异常阈值选择。相反,我们的防御是基于以这种广义的方式从训练数据中提取信息,使得我们可以基于存在于数据的未被占部分中存在的信息来识别中毒样本。我们评估我们对两个DOS中毒攻击和七个数据集的防御,并发现它可靠地识别中毒实例。与相关的工作相比,我们的防范将误报/假负率提高至少50%,通常更多。
translated by 谷歌翻译
We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the training dataset such that the impact on the model's predictions is minimal. The adversary subsequently triggers a request to remove a subset of the introduced points at which point the attack is unleashed and the model's predictions are negatively affected. In particular, we consider clean-label targeted attacks (in which the goal is to cause the model to misclassify a specific test point) on datasets including CIFAR-10, Imagenette, and Imagewoof. This attack is realized by constructing camouflage datapoints that mask the effect of a poisoned dataset.
translated by 谷歌翻译
计算能力和大型培训数据集的可用性增加,机器学习的成功助长了。假设它充分代表了在测试时遇到的数据,则使用培训数据来学习新模型或更新现有模型。这种假设受到中毒威胁的挑战,这种攻击会操纵训练数据,以损害模型在测试时的表现。尽管中毒已被认为是行业应用中的相关威胁,到目前为止,已经提出了各种不同的攻击和防御措施,但对该领域的完整系统化和批判性审查仍然缺失。在这项调查中,我们在机器学习中提供了中毒攻击和防御措施的全面系统化,审查了过去15年中该领域发表的100多篇论文。我们首先对当前的威胁模型和攻击进行分类,然后相应地组织现有防御。虽然我们主要关注计算机视觉应用程序,但我们认为我们的系统化还包括其他数据模式的最新攻击和防御。最后,我们讨论了中毒研究的现有资源,并阐明了当前的局限性和该研究领域的开放研究问题。
translated by 谷歌翻译
Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to an attacker, either through the models' structure or their observable behavior. However, the underlying cause of this privacy risk is not well understood beyond a handful of anecdotal accounts that suggest overfitting and influence might play a role.This paper examines the effect that overfitting and influence have on the ability of an attacker to learn information about the training data from machine learning models, either through training set membership inference or attribute inference attacks. Using both formal and empirical analyses, we illustrate a clear relationship between these factors and the privacy risk that arises in several popular machine learning algorithms. We find that overfitting is sufficient to allow an attacker to perform membership inference and, when the target attribute meets certain conditions about its influence, attribute inference attacks. Interestingly, our formal analysis also shows that overfitting is not necessary for these attacks and begins to shed light on what other factors may be in play. Finally, we explore the connection between membership inference and attribute inference, showing that there are deep connections between the two that lead to effective new attacks.
translated by 谷歌翻译
属性推理攻击使对手可以从机器学习模型中提取培训数据集的全局属性。此类攻击对共享数据集来培训机器学习模型的数据所有者具有隐私影响。已经提出了几种针对深神经网络的财产推理攻击的现有方法,但它们都依靠攻击者训练大量的影子模型,这会导致大型计算开销。在本文中,我们考虑了攻击者可以毒化训练数据集的子集并查询训练有素的目标模型的属性推理攻击的设置。通过我们对中毒下模型信心的理论分析的激励,我们设计了有效的财产推理攻击,SNAP,该攻击获得了更高的攻击成功,并且需要比Mahloujifar Et的基于最先进的中毒的财产推理攻击更高的中毒量。 al。例如,在人口普查数据集上,SNAP的成功率比Mahloujifar等人高34%。同时更快56.5倍。我们还扩展了攻击,以确定在培训中是否根本存在某个财产,并有效地估算了利息财产的确切比例。我们评估了对四个数据集各种比例的多种属性的攻击,并证明了Snap的一般性和有效性。
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
上下文强盗算法在各种情况下有许多申请人。为了开发值得信赖的情境强盗系统,了解各种对抗性攻击对上下文强盗算法的影响至关重要。在本文中,我们提出了一类新的攻击:动作中毒攻击,其中一个对手可以改变代理选择的动作信号。我们在白盒和黑匣子设置中设计了针对线性上下文强盗算法的动作中毒攻击方案。我们进一步分析了拟议的攻击策略的成本,非常流行和广泛使用的强盗算法:Linucb。我们展示,在白盒和黑匣子设置中,所提出的攻击方案可以强制Linucb代理通过仅度过对数成本而频繁地提取目标手臂。
translated by 谷歌翻译
从外界培训的机器学习模型可能会被数据中毒攻击损坏,将恶意指向到模型的培训集中。对这些攻击的常见防御是数据消毒:在培训模型之前首先过滤出异常培训点。在本文中,我们开发了三次攻击,可以绕过广泛的常见数据消毒防御,包括基于最近邻居,训练损失和奇异值分解的异常探测器。通过增加3%的中毒数据,我们的攻击成功地将Enron垃圾邮件检测数据集的测试错误从3%增加到24%,并且IMDB情绪分类数据集从12%到29%。相比之下,没有明确占据这些数据消毒防御的现有攻击被他们击败。我们的攻击基于两个想法:(i)我们协调我们的攻击将中毒点彼此放置在彼此附近,(ii)我们将每个攻击制定为受限制的优化问题,限制旨在确保中毒点逃避检测。随着这种优化涉及解决昂贵的Bilevel问题,我们的三个攻击对应于基于影响功能的近似近似这个问题的方式; minimax二元性;和karush-kuhn-tucker(kkt)条件。我们的结果强调了对数据中毒攻击产生更强大的防御的必要性。
translated by 谷歌翻译
机器学习与服务(MLAAS)已成为广泛的范式,即使是通过例如,也是客户可用的最复杂的机器学习模型。一个按要求的原则。这使用户避免了数据收集,超参数调整和模型培训的耗时过程。但是,通过让客户访问(预测)模型,MLAAS提供商危害其知识产权,例如敏感培训数据,优化的超参数或学到的模型参数。对手可以仅使用预测标签创建模型的副本,并以(几乎)相同的行为。尽管已经描述了这种攻击的许多变体,但仅提出了零星的防御策略,以解决孤立的威胁。这增加了对模型窃取领域进行彻底系统化的必要性,以全面了解这些攻击是成功的原因,以及如何全面地捍卫它们。我们通过对模型窃取攻击,评估其性能以及探索不同设置中相应的防御技术来解决这一问题。我们为攻击和防御方法提出了分类法,并提供有关如何根据目标和可用资源选择正确的攻击或防御策略的准则。最后,我们分析了当前攻击策略使哪些防御能力降低。
translated by 谷歌翻译
人类活动识别(HAR)是使用有效的机器学习(ML)方法将传感器数据解释为人类运动的问题。 HAR系统依靠来自不受信任的用户的数据,使他们容易受到数据中毒攻击的影响。在中毒攻击中,攻击者操纵传感器读数以污染训练集,从而误导了har以产生错误的结果。本文介绍了针对HAR系统的标签翻转数据中毒攻击的设计,在数据收集阶段,传感器读数的标签发生了恶意更改。由于传感环境中的噪音和不确定性,这种攻击对识别系统构成了严重威胁。此外,当将活动识别模型部署在安全至关重要的应用中时,标记翻转攻击的脆弱性是危险的。本文阐明了如何通过基于智能手机的传感器数据收集应用程序在实践中进行攻击。据我们所知,这是一项较早的研究工作,它通过标签翻转中毒探索了攻击HAR模型。我们实施了提出的攻击并根据以下机器学习算法进行活动识别模型进行测试:多层感知器,决策树,随机森林和XGBoost。最后,我们评估了针对拟议攻击的基于K-Nearest邻居(KNN)的防御机制的有效性。
translated by 谷歌翻译
后门攻击已被证明是对深度学习模型的严重安全威胁,并且检测给定模型是否已成为后门成为至关重要的任务。现有的防御措施主要建立在观察到后门触发器通常尺寸很小或仅影响几个神经元激活的观察结果。但是,在许多情况下,尤其是对于高级后门攻击,违反了上述观察结果,阻碍了现有防御的性能和适用性。在本文中,我们提出了基于新观察的后门防御范围。也就是说,有效的后门攻击通常需要对中毒训练样本的高预测置信度,以确保训练有素的模型具有很高的可能性。基于此观察结果,Dtinspector首先学习一个可以改变最高信心数据的预测的补丁,然后通过检查在低信心数据上应用学习补丁后检查预测变化的比率来决定后门的存在。对五次后门攻击,四个数据集和三种高级攻击类型的广泛评估证明了拟议防御的有效性。
translated by 谷歌翻译
中毒攻击已成为对机器学习算法的重要安全威胁。已经证明对培训集进行小变化的对手,例如添加特制的数据点,可以损害输出模型的性能。一些更强大的中毒攻击需要全面了解培训数据。这种叶子打开了使用没有完全了解干净训练集的中毒攻击来实现相同的攻击结果的可能性。在这项工作中,我们启动了对上述问题的理论研究。具体而言,对于具有套索的特征选择的情况,我们表明全信息对手(基于培训数据的其余部分的工艺中毒示例)可从未获得培训集的最佳攻击者提供了更强的最佳攻击者数据分发。我们的分离结果表明,数据感知和数据疏忽的两个设置从根本上不同,我们不能希望在这些场景中始终达到相同的攻击或辩护。
translated by 谷歌翻译
大量工作表明,机器学习(ML)模型可以泄漏有关其培训数据的敏感或机密信息。最近,由于分布推断(或属性推断)攻击引起的泄漏正在引起人们的注意。在此攻击中,对手的目标是推断有关培训数据的分配信息。到目前为止,对分布推理的研究集中在证明成功的攻击上,而很少注意确定泄漏的潜在原因和提出缓解。为了弥合这一差距,作为我们的主要贡献,我们从理论和经验上分析了信息泄漏的来源,这使对手能够进行分布推理攻击。我们确定泄漏的三个来源:(1)记住有关$ \ mathbb {e} [y | x] $(给定特征值的预期标签)的特定信息,((2)模型的错误归纳偏置,以及(3)培训数据的有限性。接下来,根据我们的分析,我们提出了针对分配推理攻击的原则缓解技术。具体而言,我们证明了因果学习技术比相关学习方法更适合特定类型的分布推理所谓的分配构件推理。最后,我们提出了分布推断的形式化,该推论允许对比以前更多的一般对手进行推理。
translated by 谷歌翻译
最近对机器学习(ML)模型的攻击,例如逃避攻击,具有对抗性示例,并通过提取攻击窃取了一些模型,构成了几种安全性和隐私威胁。先前的工作建议使用对抗性训练从对抗性示例中保护模型,以逃避模型的分类并恶化其性能。但是,这种保护技术会影响模型的决策边界及其预测概率,因此可能会增加模型隐私风险。实际上,仅使用对模型预测输出的查询访问的恶意用户可以提取它并获得高智能和高保真替代模型。为了更大的提取,这些攻击利用了受害者模型的预测概率。实际上,所有先前关于提取攻击的工作都没有考虑到出于安全目的的培训过程中的变化。在本文中,我们提出了一个框架,以评估具有视觉数据集对对抗训练的模型的提取攻击。据我们所知,我们的工作是第一个进行此类评估的工作。通过一项广泛的实证研究,我们证明了受对抗训练的模型比在自然训练情况下获得的模型更容易受到提取攻击的影响。他们可以达到高达$ \ times1.2 $更高的准确性和同意,而疑问低于$ \ times0.75 $。我们还发现,与从自然训练的(即标准)模型中提取的DNN相比,从鲁棒模型中提取的对抗性鲁棒性能力可通过提取攻击(即从鲁棒模型提取的深神经网络(DNN)提取的深神网络(DNN))传递。
translated by 谷歌翻译
许多最先进的ML模型在各种任务中具有优于图像分类的人类。具有如此出色的性能,ML模型今天被广泛使用。然而,存在对抗性攻击和数据中毒攻击的真正符合ML模型的稳健性。例如,Engstrom等人。证明了最先进的图像分类器可以容易地被任意图像上的小旋转欺骗。由于ML系统越来越纳入安全性和安全敏感的应用,对抗攻击和数据中毒攻击构成了相当大的威胁。本章侧重于ML安全的两个广泛和重要的领域:对抗攻击和数据中毒攻击。
translated by 谷歌翻译
有针对性的训练集攻击将恶意实例注入训练集中,以导致训练有素的模型错误地标记一个或多个特定的测试实例。这项工作提出了目标识别的任务,该任务决定了特定的测试实例是否是训练集攻击的目标。目标识别可以与对抗性识别相结合,以查找(并删除)攻击实例,从而减轻对其他预测的影响,从而减轻攻击。我们没有专注于单个攻击方法或数据模式,而是基于影响力估计,这量化了每个培训实例对模型预测的贡献。我们表明,现有的影响估计量的不良实际表现通常来自于他们对训练实例和迭代次数的过度依赖。我们重新归一化的影响估计器解决了这一弱点。他们的表现远远超过了原始估计量,可以在对抗和非对抗环境中识别有影响力的训练示例群体,甚至发现多达100%的对抗训练实例,没有清洁数据误报。然后,目标识别简化以检测具有异常影响值的测试实例。我们证明了我们的方法对各种数据域的后门和中毒攻击的有效性,包括文本,视觉和语音,以及针对灰色盒子的自适应攻击者,该攻击者专门优化了逃避我们方法的对抗性实例。我们的源代码可在https://github.com/zaydh/target_indistification中找到。
translated by 谷歌翻译
Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses that can withstand most attacks. However, abundant real-world evidence suggests that actual attackers use simple tactics to subvert ML-driven systems, and as a result security practitioners have not prioritized adversarial ML defenses. Motivated by the apparent gap between researchers and practitioners, this position paper aims to bridge the two domains. We first present three real-world case studies from which we can glean practical insights unknown or neglected in research. Next we analyze all adversarial ML papers recently published in top security conferences, highlighting positive trends and blind spots. Finally, we state positions on precise and cost-driven threat modeling, collaboration between industry and academia, and reproducible research. We believe that our positions, if adopted, will increase the real-world impact of future endeavours in adversarial ML, bringing both researchers and practitioners closer to their shared goal of improving the security of ML systems.
translated by 谷歌翻译