ترغب بنشر مسار تعليمي؟ اضغط هنا

MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models

127   0   0.0 ( 0 )
 نشر من قبل Sumit Mukherjee
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

In this work, we formally study the membership privacy risk of generative models and propose a membership privacy estimation framework. We formulate the membership privacy risk as a statistical divergence between training samples and hold-out samples, and propose sample-based methods to estimate this divergence. Unlike previous works, our proposed metric and estimators make realistic and flexible assumptions. First, we offer a generalizable metric as an alternative to accuracy for imbalanced datasets. Second, our estimators are capable of estimating the membership privacy risk given any scalar or vector valued attributes from the learned model, while prior work require access to specific attributes. This allows our framework to provide data-driven certificates for trained generative models in terms of membership privacy risk. Finally, we show a connection to differential privacy, which allows our proposed estimators to be used to understand the privacy budget epsilon needed for differentially private generative models. We demonstrate the utility of our framework through experimental demonstrations on different generative models using various model attributes yielding some new insights about membership leakage and vulnerabilities of models.



قيم البحث

اقرأ أيضاً

The huge computation demand of deep learning models and limited computation resources on the edge devices calls for the cooperation between edge device and cloud service by splitting the deep models into two halves. However, transferring the intermed iates results from the partial models between edge device and cloud service makes the user privacy vulnerable since the attacker can intercept the intermediate results and extract privacy information from them. Existing research works rely on metrics that are either impractical or insufficient to measure the effectiveness of privacy protection methods in the above scenario, especially from the aspect of a single user. In this paper, we first present a formal definition of the privacy protection problem in the edge-cloud system running DNN models. Then, we analyze the-state-of-the-art methods and point out the drawbacks of their methods, especially the evaluation metrics such as the Mutual Information (MI). In addition, we perform several experiments to demonstrate that although existing methods perform well under MI, they are not effective enough to protect the privacy of a single user. To address the drawbacks of the evaluation metrics, we propose two new metrics that are more accurate to measure the effectiveness of privacy protection methods. Finally, we highlight several potential research directions to encourage future efforts addressing the privacy protection problem.
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 t he 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 investigate and analyze membership attacks to understand why and how they succeed. Based on this understanding, we propose Differential Training Privacy (DTP), an empirical metric to estimate the privacy risk of publishing a classier when methods such as differential privacy cannot be applied. DTP is a measure of a classier with respect to its training dataset, and we show that calculating DTP is efficient in many practical cases. We empirically validate DTP using state-of-the-art machine learning models such as neural networks trained on real-world datasets. Our results show that DTP is highly predictive of the success of membership attacks and therefore reducing DTP also reduces the privacy risk. We advocate for DTP to be used as part of the decision-making process when considering publishing a classifier. To this end, we also suggest adopting the DTP-1 hypothesis: if a classifier has a DTP value above 1, it should not be published.
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, t hrough 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 membership inference attacks is routinely increased when models use skewed training data. Finally, we investigate the effectiveness of differential privacy as a mitigation technique against membership inference attacks. We discuss the trade-offs of implementing such a mitigation strategy with respect to the model complexity, the learning task complexity, the dataset complexity and the privacy parameter settings. Our empirical results reveal that (1) minority groups within skewed datasets display increased risk for membership inference and (2) differential privacy presents many challenging trade-offs as a mitigation technique to membership inference risk.
272 - Jie Ding , Bangjun Ding 2021
The emerging public awareness and government regulations of data privacy motivate new paradigms of collecting and analyzing data transparent and acceptable to data owners. We present a new concept of privacy and corresponding data formats, mechanisms , and tradeoffs for privatizing data during data collection. The privacy, named Interval Privacy, enforces the raw data conditional distribution on the privatized data to be the same as its unconditional distribution over a nontrivial support set. Correspondingly, the proposed privacy mechanism will record each data value as a random interval containing it. The proposed interval privacy mechanisms can be easily deployed through most existing survey-based data collection paradigms, e.g., by asking a respondent whether its data value is within a randomly generated range. Another unique feature of interval mechanisms is that they obfuscate the truth but not distort it. The way of using narrowed range to convey information is complementary to the popular paradigm of perturbing data. Also, the interval mechanisms can generate progressively refined information at the discretion of individual respondents. We study different theoretical aspects of the proposed privacy. In the context of supervised learning, we also offer a method such that existing supervised learning algorithms designed for point-valued data could be directly applied to learning from interval-valued data.
Membership Inference Attack (MIA) determines the presence of a record in a machine learning models training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or when the adv ersary controls the training algorithm. However, when the model is not overfitted and the adversary does not control the training algorithm, the threat is not well understood. In this paper, we report a study that discovers overfitting to be a sufficient but not a necessary condition for an MIA to succeed. More specifically, we demonstrate that even a well-generalized model contains vulnerable instances subject to a new generalized MIA (GMIA). In GMIA, we use novel techniques for selecting vulnerable instances and detecting their subtle influences ignored by overfitting metrics. Specifically, we successfully identify individual records with high precision in real-world datasets by querying black-box machine learning models. Further we show that a vulnerable record can even be indirectly attacked by querying other related records and existing generalization techniques are found to be less effective in protecting the vulnerable instances. Our findings sharpen the understanding of the fundamental cause of the problem: the unique influences the training instance may have on the model.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا