Optimizing membership inference attacks against low self-influence samples by distilled shadow models and inference models

Membership inference (MI) attacks highlight a privacy weakness in present stochastic training methods for neural networks. It is not well understood, however, why they arise. Are they a natural consequence of imperfect generalization only? Which underlying causes should we address during training to mitigate these attacks? Towards answering such questions, we propose the first approach to explain MI attacks and their connection to generalization based on principled causal reasoning. We offer causal graphs that quantitatively explain the observed MI attack performance achieved for $6$ attack variants. We refute several prior non-quantitative hypotheses that over-simplify or over-estimate the influence of underlying causes, thereby failing to capture the complex interplay between several factors. Our causal models also show a new connection between generalization and MI attacks via their shared causal factors. Our causal models have high predictive power ($0.90$), i.e., their analytical predictions match with observations in unseen experiments often, which makes analysis via them a pragmatic alternative.

Conventional membership inference attacks usually require a large number of queries of the target model when training shadow models, and this task becomes extremely difficult when the number of queries is limited. Aiming at the problem of insufficient training data for shadow models due to the limited number of queries, we propose a membership inference attack method based on generative adversarial networks (GAN). First, we use generative adversarial networks to augment the samples obtained by a small number of queries to expand the training data of the model; Secondly, we use the improved CNN to obtain shadow models that have a higher degree of fitting on different target model structures; Finally, we evaluate the accuracy of the proposed algorithm on XgBoost, Logistic, and neural network models using public datasets MNIST and CIFAR10 in a black-box setting, and the results show that our model has an average attack accuracy of 62% and 83%, respectively. It can be seen that, compared with the existing research methods, our model can obtain better attack effects under the condition of significantly reducing the number of queries, which shows the feasibility of our proposed method in membership inference attacks.

Membership inference attacks (MIAs) are important measures to evaluate potential risks of privacy leakage from machine learning (ML) models. State-of-the-art MIA defenses have achieved favorable privacy-utility trade-offs using knowledge distillation on split training datasets. However, such defenses increase computational costs as a large number of the ML models must be trained on the split datasets. In this study, we proposed a new MIA defense, called SEDMA, based on self-distillation using model aggregation to mitigate the MIAs, inspired by the model parameter averaging as used in federated learning. The key idea of SEDMA is to split the training dataset into several parts and aggregate multiple ML models trained on each split for self-distillation. The intuitive explanation of SEDMA is that model aggregation prevents model over-fitting by smoothing information related to the training data among the multiple ML models and preserving the model utility, such as in federated learning. Through our experiments on major benchmark datasets (Purchase100, Texas100, and CIFAR100), we show that SEDMA outperforms state-of-the-art MIA defenses in terms of membership privacy (MIA accuracy), model accuracy, and computational costs. Specifically, SEDMA incurs at most approximately 3 - 5% model accuracy drop, while achieving the lowest MIA accuracy in state-of-the-art empirical MIA defenses. For computational costs, SEDMA takes significantly less processing time than a defense with the state-of-the-art privacy-utility trade-offs in previous defenses. SEDMA achieves both favorable privacy-utility trade-offs and low computational costs.

Deep Learning(DL) techniques have gained significant importance in the recent past due to their vast applications. However, DL is still prone to several attacks, such as the Membership Inference Attack (MIA), based on the memorability of training data. MIA aims at determining the presence of specific data in the training dataset of the model with substitute model of similar structure to the objective model. As MIA relies on the substitute model, they can be mitigated if the substitute model is not clear about the network structure of the objective model. To solve the challenge of shadow-model construction, this work presents L-Leaks, a member inference attack based on Logits. L-Leaks allow an adversary to use the substitute model's information to predict the presence of membership if the shadow and objective model are similar enough. Here, the substitute model is built by learning the logits of the objective model, hence making it similar enough. This results in the substitute model having sufficient confidence in the member samples of the objective model. The evaluation of the attack's success shows that the proposed technique can execute the attack more accurately than existing techniques. It also shows that the proposed MIA is significantly robust under different network models and datasets.

While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by membership inference (MI) attack. Most of the existing MI attack algorithms focus on classification models, while Re-ID follows a totally different training and inference paradigm. Re-ID is a fine-grained recognition task with complex feature embedding, and model outputs commonly used by existing MI like logits and losses are not accessible during inference. Since Re-ID focuses on modelling the relative relationship between image pairs instead of individual semantics, we conduct a formal and empirical analysis which validates that the distribution shift of the inter-sample similarity between training and test set is a critical criterion for Re-ID membership inference. As a result, we propose a novel membership inference attack method based on the inter-sample similarity distribution. Specifically, a set of anchor images are sampled to represent the similarity distribution conditioned on a target image, and a neural network with a novel anchor selection module is proposed to predict the membership of the target image. Our experiments validate the effectiveness of the proposed approach on both the Re-ID task and conventional classification task.

Location data is frequently collected from populations and shared in aggregate form to guide policy and decision making. However, the prevalence of aggregated data also raises the privacy concern of membership inference attacks (MIAs). MIAs infer whether an individual's data contributed to the aggregate release. Although effective MIAs have been developed for aggregate location data, these require access to an extensive auxiliary dataset of individual traces over the same locations, which are collected from a similar population. This assumption is often impractical given common privacy practices surrounding location data. To measure the risk of an MIA performed by a realistic adversary, we develop the first Zero Auxiliary Knowledge (ZK) MIA on aggregate location data, which eliminates the need for an auxiliary dataset of real individual traces. Instead, we develop a novel synthetic approach, such that suitable synthetic traces are generated from the released aggregate. We also develop methods to correct for bias and noise, to show that our synthetic-based attack is still applicable when privacy mechanisms are applied prior to release. Using two large-scale location datasets, we demonstrate that our ZK MIA matches the state-of-the-art Knock-Knock (KK) MIA across a wide range of settings, including popular implementations of differential privacy (DP) and suppression of small counts. Furthermore, we show that ZK MIA remains highly effective even when the adversary only knows a small fraction (10%) of their target's location history. This demonstrates that effective MIAs can be performed by realistic adversaries, highlighting the need for strong DP protection.

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS). Recently, the first membership inference attack has shown that extraction of information on the training set is possible in such MLaaS settings, which has severe security and privacy implications. However, the early demonstrations of the feasibility of such attacks have many assumptions on the adversary, such as using multiple so-called shadow models, knowledge of the target model structure, and having a dataset from the same distribution as the target model's training data. We relax all these key assumptions, thereby showing that such attacks are very broadly applicable at low cost and thereby pose a more severe risk than previously thought. We present the most comprehensive study so far on this emerging and developing threat using eight diverse datasets which show the viability of the proposed attacks across domains. In addition, we propose the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.

Membership inference attack for beluga whales discrimination

The data-intensive nature of Diffusion models amplifies the risks of privacy infringements and copyright disputes, particularly when training on extensive unauthorized data scraped from the Internet. Membership Inference Attacks (MIA) aim to determine whether a data sample has been utilized by the target model during training, thereby serving as a pivotal tool for privacy preservation. Current MIA employs the prediction loss to distinguish between training member samples and non-members. These methods assume that, compared to non-members, members, having been encountered by the model during training result in a smaller prediction loss. However, this assumption proves ineffective in diffusion models due to the random noise sampled during the training process. Rather than estimating the loss, our approach examines this random noise and reformulate the MIA as a noise search problem, assuming that members are more feasible to find the noise used in the training process. We formulate this noise search process as an optimization problem and employ the fixed-point iteration to solve it. We analyze current MIA methods through the lens of the noise search framework and reveal that they rely on the first residual as the discriminative metric to differentiate members and non-members. Inspired by this observation, we introduce OMS, which augments existing MIA methods by iterating One More fixed-point Step to include a further residual, i.e., the second residual. We integrate our method into various MIA methods across different diffusion models. The experimental results validate the efficacy of our proposed approach.

Federated learning provides a solution for data privacy protection, while enabling training over the local data samples, without exchanging them. However, it is far from practical and secure because data privacy is still vulnerable due to the well-studied attacks, e.g., membership inference attacks and model inversion attacks. In this paper, to further prevent data leakage against these attacks, we propose FL-PATE, a differentially private federated learning framework with knowledge transfer. Specifically, participants with sensitive data are grouped to train teacher models under federated learning settings, and the knowledge of teacher models is transferred to a publicly accessible student model for prediction via aggregating teacher models' outputs of public datasets. A modified client-level differential privacy mechanism is used to guarantee each participant's data privacy during the corresponding teacher model's training process. The proposed framework preserves participant's privacy against membership inference attacks and the differential privacy cost is fixed. The privacy analysis and experiments demonstrate that trained teacher and student models have an excellent performance in accuracy and robustness theoretically and empirically.

With breakthroughs in high-resolution image generation, applications for disentangled generative adversarial networks (GANs) have attracted much attention. At the same time, the privacy issues associated with GAN models have been raising many concerns. Membership inference attacks (MIAs), where an adversary attempts to determine whether or not a sample has been used to train the victim model, are a major risk with GANs. In prior research, scholars have shown that successful MIAs can be mounted by leveraging overfit images. However, high-resolution images make the existing MIAs fail due to their complexity. And the nature of disentangled GANs is such that the attributes are overfitting, which means that, for an MIA to be successful, it must likely be based on overfitting attributes. Furthermore, given the empirical difficulties with obtaining independent and identically distributed (IID) candidate samples, choosing the non-trivial attributes of candidate samples as the target for exploring overfitting would be a more preferable choice. Hence, in this paper, we propose a series of attribute-based MIAs that considers both black-box and white-box settings. The attacks are performed on the generator, and the inferences are derived by overfitting the non-trivial attributes. Additionally, we put forward a novel perspective on model generalization and a possible defense by evaluating the overfitting status of each individual attribute. A series of empirical evaluations in both settings demonstrate that the attacks remain stable and successful when using non-IID candidate samples. Further experiments illustrate that each attribute exhibits a distinct overfitting status. Moreover, manually generalizing highly overfitting attributes significantly reduces the risk of privacy leaks.

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. MIAs on ML models can directly lead to a privacy breach. For example, via identifying the fact that a clinical record that has been used to train a model associated with a certain disease, an attacker can infer that the owner of the clinical record has the disease with a high chance. In recent years, MIAs have been shown to be effective on various ML models, e.g., classification models and generative models. Meanwhile, many defense methods have been proposed to mitigate MIAs. Although MIAs on ML models form a newly emerging and rapidly growing research area, there has been no systematic survey on this topic yet. In this article, we conduct the first comprehensive survey on membership inference attacks and defenses. We provide the taxonomies for both attacks and defenses, based on their characterizations, and discuss their pros and cons. Based on the limitations and gaps identified in this survey, we point out several promising future research directions to inspire the researchers who wish to follow this area. This survey not only serves as a reference for the research community but also provides a clear description for researchers outside this research domain. To further help the researchers, we have created an online resource repository, which we will keep updated with future relevant work. Interested readers can find the repository at https://github.com/HongshengHu/membership-inference-machine-learning-literature.

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on performance metrics such as AUC, accuracy, and TPR@low FPR—either by developing new methods to enhance these metrics or using them to evaluate privacy solutions—we found that it overlooks the disparities among different attacks. These disparities, both between distinct attack methods and between multiple instantiations of the same method, have crucial implications for the reliability and completeness of MIAs as privacy evaluation tools. In this paper, we systematically investigate these disparities through a novel framework based on coverage and stability analysis. Extensive experiments reveal significant disparities in MIAs, their potential causes, and their broader implications for privacy evaluation. To address these challenges, we propose an ensemble framework with three distinct strategies to harness the strengths of state-of-the-art MIAs while accounting for their disparities. This framework not only enables the construction of more powerful attacks but also provides a more robust and comprehensive methodology for privacy evaluation.

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security domain and the privacy domain have typically been considered separately. It is thus unclear whether the defense methods in one domain will have any unexpected impact on the other domain. In this paper, we take a step towards resolving this limitation by combining the two domains. In particular, we measure the success of membership inference attacks against six state-of-the-art defense methods that mitigate the risk of adversarial examples (i.e., evasion attacks). Membership inference attacks determine whether or not an individual data record has been part of a model's training set. The accuracy of such attacks reflects the information leakage of training algorithms about individual members of the training set. Adversarial defense methods against adversarial examples influence the model's decision boundaries such that model predictions remain unchanged for a small area around each input. However, this objective is optimized on training data. Thus, individual data records in the training set have a significant influence on robust models. This makes the models more vulnerable to inference attacks. To perform the membership inference attacks, we leverage the existing inference methods that exploit model predictions. We also propose two new inference methods that exploit structural properties of robust models on adversarially perturbed data. Our experimental evaluation demonstrates that compared with the natural training (undefended) approach, adversarial defense methods can indeed increase the target model's risk against membership inference attacks. When using adversarial defenses to train the robust models, the membership inference advantage increases by up to 4.5 times compared to the naturally undefended models. Beyond revealing the privacy risks of adversarial defenses, we further investigate the factors, such as model capacity, that influence the membership information leakage.

Membership inference attacks can infer whether a data sample exists in the training set of the target model based on limited adversary knowledge, which results in serious leakage of privacy. A large number of recent studies have shown that model overfitting is one of the main reasons why membership inference attacks can be executed successfully. Therefore, some classic methods to solve model overfitting are used to defend against membership inference attacks, such as dropout, spatial dropout, and differential privacy. However, it is difficult for these defense methods to achieve an available trade-off in defense success rate and model utility. In this paper, we focus on the impact of model training loss on model overfitting, and we design a Squeeze-Loss strategy to dynamically find the training loss that achieves the best balance between model utility and privacy. Extensive experimental results show that our strategy can limit the success rate of membership inference attacks to the level of random guesses with almost no loss of model utility, which always outperforms other defense methods.KeywordsMembership inference attackSqueeze training lossDeep learningData privacyDefense strategy