While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary aims to determine whether a target data sample is part of the training set of a target ML model. So far, most of the current membership inference attacks are evaluated against ML models trained from scratch. However, real-world ML models are typically trained following the transfer learning paradigm, where a model owner takes a pretrained model learned from a different dataset, namely teacher model, and trains her own student model by fine-tuning the teacher model with her own data.
In this paper, we perform the first systematic evaluation of membership inference attacks against transfer learning models. We adopt the strategy of shadow model training to derive the data for training our membership inference classifier. Extensive experiments on four real-world image datasets show that membership inference can achieve effective performance. For instance, on the CIFAR100 classifier transferred from ResNet20 (pretrained with Caltech101), our membership inference achieves $95\%$ attack AUC. Moreover, we show that membership inference is still effective when the architecture of target model is unknown. Our results shed light on the severity of membership risks stemming from machine learning models in practice.
Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion Models
The University of Auckland（奥克兰大学）；The National University of Singapore（新加坡国立大学）；The University of Melbourne（墨尔本大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique contributions. First, through MPLens, we demonstrate how membership inference attack methods can be leveraged in adversarial machine learning. Second, through MPLens, we highlight how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data itself is skewed. We show that risk from mem…
Stanford University（斯坦福大学）；Google Cloud AI Research（谷歌云人工智能研究部）
In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development. Differential privacy (DP) has emerged as one canonical standard for provable privacy. However, DP's strong theoretical guarantees often come at the cost of a large drop in its utility for machine learning, and DP guarantees themselves can be difficult to interpret. In this work, we propose a novel privacy notion, membership inference privacy (MIP), to address these challenges. We give a precise characterization o…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；National University of Singapore（新加坡国立大学）
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 curren…
Attacks that aim to identify the training data of public neural networks represent a severe threat to the privacy of individuals participating in the training data set. A possible protection is offered by anonymization of the training data or training function with differential privacy. However, data scientists can choose between local and central differential privacy and need to select meaningful privacy parameters $ε$ which is challenging for non-privacy experts. We empirically compare local and central differential privacy mechanisms under white- and black-box membership inference to evalua…
Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive datasets, more refined aggregates like the Log-Loss scores are exposed for simulating inference attacks as well as to assess the total privacy leakage based on the adversary's predictions. In this paper, we prove that this additional information enables the adversary to infer the membership of any number of datapoints with full accuracy in a single query, causing co…
University of Waterloo（滑铁卢大学）；Aalto University（阿尔托大学）
Data used to train machine learning (ML) models can be sensitive. Membership inference attacks (MIAs), attempting to determine whether a particular data record was used to train an ML model, risk violating membership privacy. ML model builders need a principled definition of a metric to quantify the membership privacy risk of (a) individual training data records, (b) computed independently of specific MIAs, (c) which assesses susceptibility to different MIAs, (d) can be used for different applications, and (e) efficiently. None of the prior membership privacy risk metrics simultaneously meet a…
Microsoft（微软）；Insitro；University of Washington（华盛顿大学）；Microsoft Research（微软研究院）
Generative machine learning models are being increasingly viewed as a way to share sensitive data between institutions. While there has been work on developing differentially private generative modeling approaches, these approaches generally lead to sub-par sample quality, limiting their use in real world applications. Another line of work has focused on developing generative models which lead to higher quality samples but currently lack any formal privacy guarantees. In this work, we propose the first formal framework for membership privacy estimation in generative models. We formulate the me…
Differentially private models seek to protect the privacy of data the model is trained on, making it an important component of model security and privacy. At the same time, data scientists and machine learning engineers seek to use uncertainty quantification methods to ensure models are as useful and actionable as possible. We explore the tension between uncertainty quantification via dropout and privacy by conducting membership inference attacks against models with and without differential privacy. We find that models with large dropout slightly increases a model's risk to succumbing to membe…
Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification accuracy, therefore creating a privacy-utility trade-off. The amount of noise that differential privacy requires to provide strong theoretical protection guarantees in deep learning typically renders the models unusable, but authors have observed that even lower noise levels provide acceptable empirical protection against existing membership inference attacks. In t…
National University of Singapore（新加坡国立大学）；NEC Corporation（NEC公司）
A membership inference attack (MIA) poses privacy risks for the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs, distillation for membership privacy (DMP), requires not only private data for protection but a large amount of unlabeled public data. However, in certain privacy-sensitive domains, such as medicine and finance, the availability of public data is not guaranteed. Moreover, a trivial method for generating public data by using generative adversarial networks sig…
We present an approach to quantify and compare the privacy-accuracy trade-off for differentially private Variational Autoencoders. Our work complements previous work in two aspects. First, we evaluate the the strong reconstruction MI attack against Variational Autoencoders under differential privacy. Second, we address the data scientist's challenge of setting privacy parameter epsilon, which steers the differential privacy strength and thus also the privacy-accuracy trade-off. In our experimental study we consider image and time series data, and three local and central differential privacy me…
A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
Universitat Rovira i Virgili（罗维拉-维格利大学）；Department of Computer Engineering（计算机工程系）；Mathematics（数学）；CYBERCAT-Center for Cybersecurity Research of Catalonia（加泰罗尼亚网络安全研究中心）；ComSCIAM-Center for Computational Science and Applied Mathematics（计算科学与应用数学研究中心）
Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and accuracy of a pruned neural network by strategically removing insignificant parameters and retraining the pruned model. Such efforts on reusing training samples pose serious privacy risks due to increased memorization, which, however, has not been investigated yet. In this paper, we conduct the first analysis of privacy risks in neural network pruning. Spec…
Princeton University（普林斯顿大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Membership inference attacks are a key measure to evaluate privacy leakage in machine learning (ML) models. These attacks aim to distinguish training members from non-members by exploiting differential behavior of the models on member and non-member inputs. The goal of this work is to train ML models that have high membership privacy while largely preserving their utility; we therefore aim for an empirical membership privacy guarantee as opposed to the provable privacy guarantees provided by techniques like differential privacy, as such techniques are shown to deteriorate model utility. Specif…
Model distillation is frequently proposed as a technique to reduce the privacy leakage of machine learning. These empirical privacy defenses rely on the intuition that distilled ``student'' models protect the privacy of training data, as they only interact with this data indirectly through a ``teacher'' model. In this work, we design membership inference attacks to systematically study the privacy provided by knowledge distillation to both the teacher and student training sets. Our new attacks show that distillation alone provides only limited privacy across a number of domains. We explain the…
University of California San Diego（加州大学圣地亚哥分校）；Toyota Technological Institute at Chicago (TTIC)（芝加哥丰田技术研究所）；University of Virginia（弗吉尼亚大学）；National University of Singapore（新加坡国立大学）
The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information about their training data? Prior attempts at measuring leakage of MLMs via membership inference attacks have been inconclusive, implying the potential robustness of MLMs to privacy attacks. In this work, we posit that prior attempts were inconclusive because they based their attack solely on the MLM's model score. We devise a stronger membership inference atta…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Stanford University（斯坦福大学）；Google（谷歌）
Membership inference attacks are one of the simplest forms of privacy leakage for machine learning models: given a data point and model, determine whether the point was used to train the model. Existing membership inference attacks exploit models' abnormal confidence when queried on their training data. These attacks do not apply if the adversary only gets access to models' predicted labels, without a confidence measure. In this paper, we introduce label-only membership inference attacks. Instead of relying on confidence scores, our attacks evaluate the robustness of a model's predicted labels…
University of Virginia（弗吉尼亚大学）；University of Lausanne（洛桑大学）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Carnegie Mellon University（卡内基梅隆大学）；Purdue University（普渡大学）
The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten requires an ML model owner to remove the data owner's data from the training set used to build the ML model, a process known as machine unlearning. While originally designed to protect the privacy of the data owner, we argue that machine unlearning may leave some imprint of the data in the ML model and thus create unintended privacy risks. In this paper, we perform the first study on investigating the unintended infor…
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Salesforce Research（赛富时研究院）
Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requires huge amounts of data that might contain privacy-sensitive information, e.g., face identity. While privacy risks have been extensively demonstrated in the image classification and GAN generation domains, privacy risks in the text-to-image generation domain are largely unexplored. In this paper, we perform the first privacy analysis of text-to-image generation models through the lens of membership inference. Specif…
Historically, machine learning methods have not been designed with security in mind. In turn, this has given rise to adversarial examples, carefully perturbed input samples aimed to mislead detection at test time, which have been applied to attack spam and malware classification, and more recently to attack image classification. Consequently, an abundance of research has been devoted to designing machine learning methods that are robust to adversarial examples. Unfortunately, there are desiderata besides robustness that a secure and safe machine learning model must satisfy, such as fairness an…
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
Institute of Science Tokyo（东京科学大学）；Nanyang Technological University（南洋理工大学）；Tohoku University（东北大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Shandong University（山东大学）
Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present the first study about membership inference attacks against diffusion models, which aims to infer whether a sample was used to train the model. Two attack methods are proposed, namely loss-based and likelihood-based attacks. Our attack methods are evaluated on several state-of-the-art diffusion models, over different datasets in relation to privacy-sensitive…
Artificial intelligence and machine learning have been integrated into all aspects of our lives and the privacy of personal data has attracted more and more attention. Since the generation of the model needs to extract the effective information of the training data, the model has the risk of leaking the privacy of the training data. Membership inference attacks can measure the model leakage of source data to a certain degree. In this paper, we design a privacy-preserving generative framework against membership inference attacks, through the information extraction and data generation capabiliti…
Group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member. Recent contributions provide privacy for group membership protocols through the joint use of two mechanisms: quantizing templates into discrete embeddings and aggregating several templates into one group representation. However, this scheme has one drawback: the data structure representing the group has a limited size and cannot recognize noisy queries when many templates are aggregated. Moreover, the sparsity of the embeddings seemingly plays a crucial …
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
Southern University of Science and Technology（南方科技大学）；Singapore University of Technology and Design（新加坡科技设计大学）；South China University of Technology（华南理工大学）；Jilin University（吉林大学）
Machine learning models are increasingly made available to the masses through public query interfaces. Recent academic work has demonstrated that malicious users who can query such models are able to infer sensitive information about records within the training data. Differential privacy can thwart such attacks, but not all models can be readily trained to achieve this guarantee or to achieve it with acceptable utility loss. As a result, if a model is trained without differential privacy guarantee, little is known or can be said about the privacy risk of releasing it. In this work, we investig…
Perspecta Labs（Perspecta实验室）；University of Maryland（马里兰大学）
We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample belongs to the dataset on which the attacked machine learning model was trained. Several approaches have been developed to mitigate this privacy leakage but the tradeoff performance implications of these defensive mechanisms (i.e., accuracy and utility of the defended machine learning model) are not well studied yet. We propose a novel approach of privacy leak…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior work on membership inference attacks may severely underestimate the privacy risks by relying solely on training custom neural network classifiers to perform attacks and focusing only on the aggregate results over data samples, such as the attack accuracy. To overcome these limitations, we first propose to benchmark membership inference privacy risks by improvin…
Max Planck Institute for Computer Science（马克斯·普朗克计算机科学研究所）
Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the victim model. Our work consists of two sides: We introduce sampling attack, a novel membership inference technique that unlike other standard membership adversaries is able to work under severe restriction of no access to scores of the victim model. We show that a victim model that only publishes the labels is still susceptible to sampling attacks and the adv…
