ترغب بنشر مسار تعليمي؟ اضغط هنا

Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees

81   0   0.0 ( 0 )
 نشر من قبل Aleksei Triastcyn
 تاريخ النشر 2020
والبحث باللغة English




اسأل ChatGPT حول البحث

This paper considers the problem of enhancing user privacy in common machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples form a generative adversarial network. We propose employing Bayesian differential privacy as the means to achieve a rigorous theoretical guarantee while providing a better privacy-utility trade-off. We demonstrate experimentally that our approach produces higher-fidelity samples, compared to prior work, allowing to (1) detect more subtle data errors and biases, and (2) reduce the need for real data labelling by achieving high accuracy when training directly on artificial samples.



قيم البحث

اقرأ أيضاً

Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their local sensitive data. In this paper, we introduce federated $f$-differen tial privacy, a new notion specifically tailored to the federated setting, based on the framework of Gaussian differential privacy. Federated $f$-differential privacy operates on record level: it provides the privacy guarantee on each individual record of one clients data against adversaries. We then propose a generic private federated learning framework {PriFedSync} that accommodates a large family of state-of-the-art FL algorithms, which provably achieves federated $f$-differential privacy. Finally, we empirically demonstrate the trade-off between privacy guarantee and prediction performance for models trained by {PriFedSync} in computer vision tasks.
The availability of genomic data is often essential to progress in biomedical research, personalized medicine, drug development, etc. However, its extreme sensitivity makes it problematic, if not outright impossible, to publish or share it. As a resu lt, several initiatives have been launched to experiment with synthetic genomic data, e.g., using generative models to learn the underlying distribution of the real data and generate artificial datasets that preserve its salient characteristics without exposing it. This paper provides the first evaluation of the utility and the privacy protection of six state-of-the-art models for generating synthetic genomic data. We assess the performance of the synthetic data on several common tasks, such as allele population statistics and linkage disequilibrium. We then measure privacy through the lens of membership inference attacks, i.e., inferring whether a record was part of the training data. Our experiments show that no single approach to generate synthetic genomic data yields both high utility and strong privacy across the board. Also, the size and nature of the training dataset matter. Moreover, while some combinations of datasets and models produce synthetic data with distributions close to the real data, there often are target data points that are vulnerable to membership inference. Looking forward, our techniques can be used by practitioners to assess the risks of deploying synthetic genomic data in the wild and serve as a benchmark for future work.
Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms. Enabling the design of datasets to test specific properties and failure modes of learning algorithms is thu s a problem of high interest, as it has a direct impact on innovation in the field. In this sense, we introduce Synbols -- Synthetic Symbols -- a tool for rapidly generating new datasets with a rich composition of latent features rendered in low resolution images. Synbols leverages the large amount of symbols available in the Unicode standard and the wide range of artistic font provided by the open font community. Our tools high-level interface provides a language for rapidly generating new distributions on the latent features, including various types of textures and occlusions. To showcase the versatility of Synbols, we use it to dissect the limitations and flaws in standard learning algorithms in various learning setups including supervised learning, active learning, out of distribution generalization, unsupervised representation learning, and object counting.
Quantum machine learning (QML) can complement the growing trend of using learned models for a myriad of classification tasks, from image recognition to natural speech processing. A quantum advantage arises due to the intractability of quantum operati ons on a classical computer. Many datasets used in machine learning are crowd sourced or contain some private information. To the best of our knowledge, no current QML models are equipped with privacy-preserving features, which raises concerns as it is paramount that models do not expose sensitive information. Thus, privacy-preserving algorithms need to be implemented with QML. One solution is to make the machine learning algorithm differentially private, meaning the effect of a single data point on the training dataset is minimized. Differentially private machine learning models have been investigated, but differential privacy has yet to be studied in the context of QML. In this study, we develop a hybrid quantum-classical model that is trained to preserve privacy using differentially private optimization algorithm. This marks the first proof-of-principle demonstration of privacy-preserving QML. The experiments demonstrate that differentially private QML can protect user-sensitive information without diminishing model accuracy. Although the quantum model is simulated and tested on a classical computer, it demonstrates potential to be efficiently implemented on near-term quantum devices (noisy intermediate-scale quantum [NISQ]). The approachs success is illustrated via the classification of spatially classed two-dimensional datasets and a binary MNIST classification. This implementation of privacy-preserving QML will ensure confidentiality and accurate learning on NISQ technology.
The goal of program synthesis is to automatically generate programs in a particular language from corresponding specifications, e.g. input-output behavior. Many current approaches achieve impressive results after training on randomly generated I/O ex amples in limited domain-specific languages (DSLs), as with string transformations in RobustFill. However, we empirically discover that applying test input generation techniques for languages with control flow and rich input space causes deep networks to generalize poorly to certain data distributions; to correct this, we propose a new methodology for controlling and evaluating the bias of synthetic data distributions over both programs and specifications. We demonstrate, using the Karel DSL and a small Calculator DSL, that training deep networks on these distributions leads to improved cross-distribution generalization performance.

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