Related papers: Privacy- and Utility-Preserving Textual Analysis v…

Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perform this task, unfortunately they can leak training data…

We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification…

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…

Differential Privacy (DP) has become a gold standard in privacy-preserving data analysis. While it provides one of the most rigorous notions of privacy, there are many settings where its applicability is limited. Our main contribution is in…

Deep learning models leak significant amounts of information about their training datasets. Previous work has investigated training models with differential privacy (DP) guarantees through adding DP noise to the gradients. However, such…

Data privacy is an important concern in machine learning, and is fundamentally at odds with the task of training useful learning models, which typically require the acquisition of large amounts of private user data. One possible way of…

Large language models (LLMs) do not preserve privacy at inference-time. The LLM's outputs can inadvertently reveal information about the model's context, which presents a privacy challenge when the LLM is augmented via tools or databases…

Private machine learning involves addition of noise while training, resulting in lower accuracy. Intuitively, greater stability can imply greater privacy and improve this privacy-utility tradeoff. We study this role of stability in private…

The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism. However, for meaningful privacy parameters, a differentially private model degrades the utility drastically when the model…

Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the…

NLP models trained with differential privacy (DP) usually adopt the DP-SGD framework, and privacy guarantees are often reported in terms of the privacy budget $\epsilon$. However, $\epsilon$ does not have any intrinsic meaning, and it is…

This study develops a novel framework for privacy-preserving data analytics, addressing the critical challenge of balancing data utility with privacy concerns. We introduce three sophisticated algorithms: a Noise-Infusion Technique tailored…

Proper communication is key to the adoption and implementation of differential privacy (DP). However, a prior study found that laypeople did not understand the data perturbation processes of DP and how DP noise protects their sensitive…

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

This paper presents a framework for privacy-preserving verification of machine learning models, focusing on models trained on sensitive data. Integrating Local Differential Privacy (LDP) with model explanations from LIME and SHAP, our…

We study model personalization under user-level differential privacy (DP) in the shared representation framework. In this problem, there are $n$ users whose data is statistically heterogeneous, and their optimal parameters share an unknown…

Hyperparameter tuning is a common practice in the application of machine learning but is a typically ignored aspect in the literature on privacy-preserving machine learning due to its negative effect on the overall privacy parameter. In…

Internet tracking technologies and wearable electronics provide a vast amount of data to machine learning algorithms. This stock of data stands to increase with the developments of the internet of things and cyber-physical systems. Clearly,…

In distributed networks, calculating the maximum element is a fundamental task in data analysis, known as the distributed maximum consensus problem. However, the sensitive nature of the data involved makes privacy protection essential.…

Text embedding inversion attacks reconstruct original sentences from latent representations, posing severe privacy threats in collaborative inference and edge computing. We propose TextCrafter, an optimization-based adversarial perturbation…