More Like this

1. Does Differential Privacy Impact Bias in Pretrained Language Models?

   Islam, MK; Wang, A; Wang, T; Ji, Y; Fox, J; Zhao, J (June 2024, IEEE Data Engineering Bulletin (Special Issue on Privacy-preserving Data Management) Vol. 48 No. 2, June 2024.)

   Wang, H; Xiao, X (Ed.)

   Differential privacy (DP) is applied when fine-tuning pre-trained language models (LMs) to limit leakage of training examples. While most DP research has focused on improving a model’s privacy-utility tradeoff, some find that DP can be unfair to or biased against underrepresented groups. In this work, we extensively analyze the impact of DP on bias in LMs. We find differentially private training can increase the model bias against protected groups w.r.t AUC-based bias metrics. DP makes it more difficult for the model to differentiate between the positive and negative examples from the protected groups and other groups in the rest of the population. Our results also show that the impact of DP on bias is affected by both the privacy protection level and the underlying distribution of the dataset. 

   more » « less
2. DPGen: Automated Program Synthesis for Differential Privacy

   Wang, Yuxin; Ding, Zeyu; Xiao, Yingtai; Kifer, Daniel; Zhang, Danfeng (January 2021, The ACM Conference on Computer and Communications Security (CCS))

   null (Ed.)

   Differential privacy has become a de facto standard for releasing data in a privacy-preserving way. Creating a differentially private algorithm is a process that often starts with a noise-free (nonprivate) algorithm. The designer then decides where to add noise, and how much of it to add. This can be a non-trivial process – if not done carefully, the algorithm might either violate differential privacy or have low utility. In this paper, we present DPGen, a program synthesizer that takes in non-private code (without any noise) and automatically synthesizes its differentially private version (with carefully calibrated noise). Under the hood, DPGen uses novel algorithms to automatically generate a sketch program with candidate locations for noise, and then optimize privacy proof and noise scales simultaneously on the sketch program. Moreover, DPGen can synthesize sophisticated mechanisms that adaptively process queries until a specified privacy budget is exhausted. When evaluated on standard benchmarks, DPGen is able to generate differentially private mechanisms that optimize simple utility functions within 120 seconds. It is also powerful enough to synthesize adaptive privacy mechanisms. 

   more » « less
3. Differentially private binary- and matrix-valued data query: an XOR mechanism

   https://doi.org/10.14778/3446095.3446106  

   Ji, Tianxi; Li, Pan; Yilmaz, Emre; Ayday, Erman; Ye, Yanfang; Sun, Jinyuan (January 2021, Proceedings of the VLDB Endowment)

   null (Ed.)

   Differential privacy has been widely adopted to release continuous- and scalar-valued information on a database without compromising the privacy of individual data records in it. The problem of querying binary- and matrix-valued information on a database in a differentially private manner has rarely been studied. However, binary- and matrix-valued data are ubiquitous in real-world applications, whose privacy concerns may arise under a variety of circumstances. In this paper, we devise an exclusive or (XOR) mechanism that perturbs binary- and matrix-valued query result by conducting an XOR operation on the query result with calibrated noises attributed to a matrix-valued Bernoulli distribution. We first rigorously analyze the privacy and utility guarantee of the proposed XOR mechanism. Then, to generate the parameters in the matrix-valued Bernoulli distribution, we develop a heuristic approach to minimize the expected square query error rate under ϵ -differential privacy constraint. Additionally, to address the intractability of calculating the probability density function (PDF) of this distribution and efficiently generate samples from it, we adapt an Exact Hamiltonian Monte Carlo based sampling scheme. Finally, we experimentally demonstrate the efficacy of the XOR mechanism by considering binary data classification and social network analysis, all in a differentially private manner. Experiment results show that the XOR mechanism notably outperforms other state-of-the-art differentially private methods in terms of utility (such as classification accuracy and F 1 score), and even achieves comparable utility to the non-private mechanisms. 

   more » « less
4. 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
5. A Programming Language for Data Privacy with Accuracy Estimations

   https://doi.org/10.1145/3452096  

   Lobo-Vesga, Elisabet; Russo, Alejandro; Gaboardi, Marco (July 2021, ACM Transactions on Programming Languages and Systems)

   Differential privacy offers a formal framework for reasoning about the privacy and accuracy of computations on private data. It also offers a rich set of building blocks for constructing private data analyses. When carefully calibrated, these analyses simultaneously guarantee the privacy of the individuals contributing their data, and the accuracy of the data analysis results, inferring useful properties about the population. The compositional nature of differential privacy has motivated the design and implementation of several programming languages to ease the implementation of differentially private analyses. Even though these programming languages provide support for reasoning about privacy, most of them disregard reasoning about the accuracy of data analyses. To overcome this limitation, we present DPella, a programming framework providing data analysts with support for reasoning about privacy, accuracy, and their trade-offs. The distinguishing feature of DPella is a novel component that statically tracks the accuracy of different data analyses. To provide tight accuracy estimations, this component leverages taint analysis for automatically inferring statistical independence of the different noise quantities added for guaranteeing privacy. We evaluate our approach by implementing several classical queries from the literature and showing how data analysts can calibrate the privacy parameters to meet the accuracy requirements, and vice versa. 

   more » « less