Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
61
0
0.0
(
0
)
Added by
Seng Pei Liew
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training deep generative models is possible without re-using the original data. Hence, no extra privacy costs or model constraints are incurred, in contrast to popular approaches such as Differentially Private Stochastic Gradient Descent (DP-SGD), which, among other issues, causes degradation in privacy guarantees as the training iteration increases. We demonstrate a realization of our framework by making use of the characteristic function and an adversarial re-weighting objective, which are of independent interest as well. Our proposal has theoretical guarantees of performance, and empirical evaluations on multiple datasets show that our approach outperforms other methods at reasonable levels of privacy.
rate research
Read More
In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset. We use generative adversarial network to draw privacy-preserving artificial data samples and derive an empirical method to assess the risk of information disclosure in a differential-privacy-like way. Our experiments show that we are able to generate artificial data of high quality and successfully train and validate machine learning models on this data while limiting potential privacy loss.
We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious dimensional dependence. Specifically, we reparametrize each weight matrix with two emph{gradient-carrier} matrices of small dimension and a emph{residual weight} matrix. We argue that such reparametrization keeps the forward/backward process unchanged while enabling us to compute the projected gradient without computing the gradient itself. To learn with differential privacy, we design emph{reparametrized gradient perturbation (RGP)} that perturbs the gradients on gradient-carrier matrices and reconstructs an update for the original weight from the noisy gradients. Importantly, we use historical updates to find the gradient-carrier matrices, whose optimality is rigorously justified under linear regression and empirically verified with deep learning tasks. RGP significantly reduces the memory cost and improves the utility. For example, we are the first able to apply differential privacy on the BERT model and achieve an average accuracy of $83.9%$ on four downstream tasks with $epsilon=8$, which is within $5%$ loss compared to the non-private baseline but enjoys much lower privacy leakage risk.
While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients privacy is a barrier against using such data to train deep neural networks (DNNs) for medical diagnostics. We propose Dopamine, a system to train DNNs on distributed datasets, which employs federated learning (FL) with differentially-private stochastic gradient descent (DPSGD), and, in combination with secure aggregation, can establish a better trade-off between differential privacy (DP) guarantee and DNNs accuracy than other approaches. Results on a diabetic retinopathy~(DR) task show that Dopamine provides a DP guarantee close to the centralized training counterpart, while achieving a better classification accuracy than FL with parallel DP where DPSGD is applied without coordination. Code is available at https://github.com/ipc-lab/private-ml-for-health.
Organizations are increasingly relying on data to support decisions. When data contains private and sensitive information, the data owner often desires to publish a synthetic database instance that is similarly useful as the true data, while ensuring the privacy of individual data records. Existing differentially private data synthesis methods aim to generate useful data based on applications, but they fail in keeping one of the most fundamental data properties of the structured data -- the underlying correlations and dependencies among tuples and attributes (i.e., the structure of the data). This structure is often expressed as integrity and schema constraints, or with a probabilistic generative process. As a result, the synthesized data is not useful for any downstream tasks that require this structure to be preserved. This work presents Kamino, a data synthesis system to ensure differential privacy and to preserve the structure and correlations present in the original dataset. Kamino takes as input of a database instance, along with its schema (including integrity constraints), and produces a synthetic database instance with differential privacy and structure preservation guarantees. We empirically show that while preserving the structure of the data, Kamino achieves comparable and even better usefulness in applications of training classification models and answering marginal queries than the state-of-the-art methods of differentially private data synthesis.
Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictions. Recently, it was proposed that this behavior can be combatted by optimizing the worst case loss function over all possible substitutions of training examples. However, this can be prone to weighing unlikely substitutions higher, limiting the accuracy gain. In this paper, we study adversarial robustness through randomized perturbations, which has two immediate advantages: (1) by ensuring that substitution likelihood is weighted by the proximity to the original word, we circumvent optimizing the worst case guarantees and achieve performance gains; and (2) the calibrated randomness imparts differentially-private model training, which additionally improves robustness against adversarial attacks on the model outputs. Our approach uses a novel density-based mechanism based on truncated Gumbel noise, which ensures training on substitutions of both rare and dense words in the vocabulary while maintaining semantic similarity for model robustness.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
