More Like this

1. Evaluating Differentially Private Machine Learning in Practice

   Jayaraman, Bargav; Evans, David (August 2019, USENIX Security Symposium)

   Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, ϵ, about how much information is leaked by a mechanism. When used in privacy-preserving machine learning, the goal is typically to limit what can be inferred from the model about individual training records. However, the calibration of the privacy budget is not well understood. Implementations of privacy-preserving machine learning often select large values of ϵ in order to get acceptable utility of the model, with little understanding of the impact of such choices on meaningful privacy. Moreover, in scenarios where iterative learning procedures are used, relaxed definitions of differential privacy are often used which appear to reduce the needed privacy budget but present poorly understood trade-offs between privacy and utility. In this paper, we quantify the impact of these choices on privacy in experiments with logistic regression and neural network models. Our main finding is that there is no way to obtain privacy for free---relaxed definitions of differential privacy that reduce the amount of noise needed to improve utility also increase the measured privacy leakage. Current mechanisms for differentially private machine learning rarely offer acceptable utility-privacy trade-offs for complex learning tasks: settings that provide limited accuracy loss provide little effective privacy, and settings that provide strong privacy result in useless models. 

   more » « less
2. Profile Based Privacy for Locally Private Computations

   Geumlek, J and (July 2019, Abstracts of papers - IEEE International Symposium on Information Theory)

   Differential privacy has emerged as a gold standard in privacy-preserving data analysis. A popular variant is local differential privacy, where the data holder is the trusted curator. A major barrier, however, towards a wider adoption of this model is that it offers a poor privacy-utility tradeoff. In this work, we address this problem by introducing a new variant of local privacy called profile-based privacy. The central idea is that the problem setting comes with a graph G of data generating distributions, whose edges encode sensitive pairs of distributions that should be made indistinguishable. This provides higher utility because unlike local differential privacy, we no longer need to make every pair of private values in the domain indistinguishable, and instead only protect the identity of the underlying distribution. We establish privacy properties of the profile-based privacy definition, such as post-processing invariance and graceful composition. Finally, we provide mechanisms that are private in this framework, and show via simulations that they achieve higher utility than the corresponding local differential privacy mechanisms. 

   more » « less
3. Differential Fairness: An Intersectional Framework for Fair AI

   https://doi.org/10.3390/e25040660  

   Islam, Rashidul; Keya, Kamrun Naher; Pan, Shimei; Sarwate, Anand D.; Foulds, James R. (April 2023, Entropy)

   We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens from the legal, social science, and humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. Our theoretical results show that our criteria meaningfully operationalize AI fairness in terms of real-world harms, making the measurements interpretable in a manner analogous to differential privacy. We provide a simple learning algorithm using deterministic gradient methods, which respects our intersectional fairness criteria. The measurement of fairness becomes statistically challenging in the minibatch setting due to data sparsity, which increases rapidly in the number of protected attributes and in the values per protected attribute. To address this, we further develop a practical learning algorithm using stochastic gradient methods which incorporates stochastic estimation of the intersectional fairness criteria on minibatches to scale up to big data. Case studies on census data, the COMPAS criminal recidivism dataset, the HHP hospitalization data, and a loan application dataset from HMDA demonstrate the utility of our methods. 

   more » « less
4. An Intersectional Definition of Fairness

   Foulds, James R.; Islam, Rashidul; Keya, Kamrun Naher; Pan, Shimei (April 2020, IEEE International Conference on Data Engineering)

   We propose differential fairness, a multi-attribute definition of fairness in machine learning which is informed by intersectionality, a critical lens arising from the humanities literature, leveraging connections between differential privacy and legal notions of fairness. We show that our criterion behaves sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our differential fairness criterion. Experiments on the COMPAS criminal recidivism dataset and census data demonstrate the utility of our methods. 

   more » « less
5. Differential Fairness

   Foulds, James R.; Islam, Rashidul; Keya, Kamrun Naher; Pan, Shimei (December 2019, NeurIPS 2019 Workshop on Machine Learning with Guarantees)

   We propose differential fairness, a multi-attribute definition of fairness in machine learning which is informed by the framework of intersectionality, a critical lens arising from the humanities literature, leveraging connections between differential privacy and legal notions of fairness. We show that our criterion behaves sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our differential fairness criterion. Experiments on the COMPAS criminal recidivism dataset and census data demonstrate the utility of our methods. 

   more » « less