More Like this

1. Differentially private synthetic mixed-type data generation for unsupervised learning

   https://doi.org/10.3233/IDT-210195  

   Tantipongpipat, Uthaipon Tao; Waites, Chris; Boob, Digvijay; Siva, Amaresh Ankit; Cummings, Rachel (January 2022, Intelligent Decision Technologies)

   Tsihrintzis, George A.; Virvou, Maria; Hatzilygeroudis, Ioannis (Ed.)

   We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs). This framework can be used to take in raw sensitive data and privately train a model for generating synthetic data that will satisfy similar statistical properties as the original data. This learned model can generate an arbitrary amount of synthetic data, which can then be freely shared due to the post-processing guarantee of differential privacy. Our framework is applicable to unlabeled mixed-type data, that may include binary, categorical, and real-valued data. We implement this framework on both binary data (MIMIC-III) and mixed-type data (ADULT), and compare its performance with existing private algorithms on metrics in unsupervised settings. We also introduce a new quantitative metric able to detect diversity, or lack thereof, of synthetic data. 

   more » « less
2. Edge Differential Privacy for Algebraic Connectivity of Graphs

   https://doi.org/10.1109/CDC45484.2021.9683306  

   Chen, Bo; Hawkins, Calvin; Yazdani, Kasra; Hale, Matthew (December 2021, Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC))

   Graphs are the dominant formalism for modeling multi-agent systems. The algebraic connectivity of a graph is particularly important because it provides the convergence rates of consensus algorithms that underlie many multi-agent control and optimization techniques. However, sharing the value of algebraic connectivity can inadvertently reveal sensitive information about the topology of a graph, such as connections in social networks. Therefore, in this work we present a method to release a graph’s algebraic connectivity under a graph-theoretic form of differential privacy, called edge differential privacy. Edge differential privacy obfuscates differences among graphs’ edge sets and thus conceals the absence or presence of sensitive connections therein. We provide privacy with bounded Laplace noise, which improves accuracy relative to conventional unbounded noise. The private algebraic connectivity values are analytically shown to provide accurate estimates of consensus convergence rates, as well as accurate bounds on the diameter of a graph and the mean distance between its nodes. Simulation results confirm the utility of private algebraic connectivity in these contexts. 

   more » « less
3. Statistical Data Privacy: A Song of Privacy and Utility

   https://doi.org/10.1146/annurev-statistics-033121-112921  

   Slavković, Aleksandra; Seeman, Jeremy (March 2023, Annual Review of Statistics and Its Application)

   To quantify trade-offs between increasing demand for open data sharing and concerns about sensitive information disclosure, statistical data privacy (SDP) methodology analyzes data release mechanisms that sanitize outputs based on confidential data. Two dominant frameworks exist: statistical disclosure control (SDC) and the more recent differential privacy (DP). Despite framing differences, both SDC and DP share the same statistical problems at their core. For inference problems, either we may design optimal release mechanisms and associated estimators that satisfy bounds on disclosure risk measures, or we may adjust existing sanitized output to create new statistically valid and optimal estimators. Regardless of design or adjustment, in evaluating risk and utility, valid statistical inferences from mechanism outputs require uncertainty quantification that accounts for the effect of the sanitization mechanism that introduces bias and/or variance. In this review, we discuss the statistical foundations common to both SDC and DP, highlight major developments in SDP, and present exciting open research problems in private inference. 

   more » « less
4. Towards Effective Differential Privacy Communication for Users’ Data Sharing Decision and Comprehension

   https://doi.org/10.1109/SP40000.2020.00088  

   Xiong, Aiping; Wang, Tianhao; Li, Ninghui; Jha, Somesh (May 2020, IEEE Symposium on Security and Privacy)

   null (Ed.)

   Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments investigating the effects of using different approaches to communicate differential privacy techniques to laypersons in a health app data collection setting. Experiments 1 and 2 investigated participants' data disclosure decisions for low-sensitive and high-sensitive personal information when given different DP or LDP descriptions. Experiments 3 and 4 uncovered reasons behind participants' data sharing decisions, and examined participants' subjective and objective comprehensions of these DP or LDP descriptions. When shown descriptions that explain the implications instead of the definition/processes of DP or LDP technique, participants demonstrated better comprehension and showed more willingness to share information with LDP than with DP, indicating their understanding of LDP's stronger privacy guarantee compared with DP. 

   more » « less
5. Differential Privacy Has Disparate Impact on Model Accuracy

   Bagdasaryan, Eugene; Poursaeed, Omid; Shmatikov, Vitaly (January 2019, Advances in neural information processing systems)

   null (Ed.)

   Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy. We demonstrate that in the neural networks trained using differentially private stochastic gradient descent (DP-SGD), this cost is not borne equally: accuracy of DP models drops much more for the underrepresented classes and subgroups. For example, a gender classification model trained using DP-SGD exhibits much lower accuracy for black faces than for white faces. Critically, this gap is bigger in the DP model than in the non-DP model, i.e., if the original model is unfair, the unfairness becomes worse once DP is applied. We demonstrate this effect for a variety of tasks and models, including sentiment analysis of text and image classification. We then explain why DP training mechanisms such as gradient clipping and noise addition have disproportionate effect on the underrepresented and more complex subgroups, resulting in a disparate reduction of model accuracy. 

   more » « less