相关论文: Differentially Private Ensemble Classifiers for Da…

In this paper, we present a notion of differential privacy (DP) for data that comes from different classes. Here, the class-membership is private information that needs to be protected. The proposed method is an output perturbation…

Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis -- even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the…

The dire need to protect sensitive data has led to various flavors of privacy definitions. Among these, Differential privacy (DP) is considered one of the most rigorous and secure notions of privacy, enabling data analysis while preserving…

We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or…

In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…

Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches…

Machine learning models used for distributed architectures consisting of servers and clients require large amounts of data to achieve high accuracy. Data obtained from clients are collected on a central server for model training. However,…

Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is…

As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of malicious leakage of sensitive private data from these systems.…

In this paper, we focus on preserving differential privacy (DP) in continual learning (CL), in which we train ML models to learn a sequence of new tasks while memorizing previous tasks. We first introduce a notion of continual adjacent…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

Decentralized Federated Learning (DFL) enables collaborative model training without a central server, but it remains vulnerable to privacy leakage because shared model updates can expose sensitive information through inversion,…

We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or…

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

In this paper, we consider differentially private classification when some features are sensitive, while the rest of the features and the label are not. We adapt the definition of differential privacy naturally to this setting. Our main…

Learning a privacy-preserving model from sensitive data which are distributed across multiple devices is an increasingly important problem. The problem is often formulated in the federated learning context, with the aim of learning a single…

Rigorous privacy mechanisms that can cope with dynamic data are required to encourage a wider adoption of large-scale monitoring and decision systems relying on end-user information. A promising approach to develop these mechanisms is to…

Kaplan-Meier estimators are essential tools in survival analysis, capturing the survival behavior of a cohort. Their accuracy improves with large, diverse datasets, encouraging data holders to collaborate for more precise estimations.…

In the pursuit of autonomous learning systems, the foundational assumption of stationarity, the premise that data distributions and model behaviors remain constant, is fundamentally untenable. Historically, the research community has…

Ensemble methods are commonly used in classification due to their remarkable performance. Achieving high accuracy in a data stream environment is a challenging task considering disruptive changes in the data distribution, also known as…