相关论文: Private Prediction via Shrinkage

We introduce a logical framework named Distributed Labeled Tagged Transition System (DLTTS), using concepts from Probabilistic Automata, Probabilistic Concurrent Systems, and Probabilistic labelled transition systems. We show that DLTTS can…

Patient privacy is a major barrier to healthcare AI. For confidentiality reasons, most patient data remains in silo in separate hospitals, preventing the design of data-driven healthcare AI systems that need large volumes of patient data to…

In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private. Compared to the classical gradient descent algorithm where updates operate on a single model vector and controlled noise…

There has been increasing demand for establishing privacy-preserving methodologies for modern statistics and machine learning. Differential privacy, a mathematical notion from computer science, is a rising tool offering robust privacy…

Differential Privacy (DP) considers a scenario in which an adversary has almost complete information about the entries of a database. This worst-case assumption is likely to overestimate the privacy threat faced by an individual in…

We give new differentially private algorithms for the classic problems of learning decision lists and large-margin halfspaces in the PAC and online models. In the PAC model, we give a computationally efficient algorithm for learning…

We introduce a new method for releasing answers to statistical queries with differential privacy, based on the Johnson-Lindenstrauss lemma. The key idea is to randomly project the query answers to a lower dimensional space so that the…

We give new mechanisms for answering exponentially many queries from multiple analysts on a private database, while protecting differential privacy both for the individuals in the database and for the analysts. That is, our mechanism's…

Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requires computation of per-sample gradients norms which is…

We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. While prior work on private contextual bandits has been restricted to linear reward models -- which…

Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective…

Differential privacy (DP) is a formal privacy framework that enables training machine learning (ML) models while protecting individuals' data. As pointed out by prior work, ML models are part of larger systems, which can lead to so-called…

We study the problem of privately computing the anonymized histogram (a.k.a. unattributed histogram), which is defined as the histogram without item labels. Previous works have provided algorithms with $\ell_1$- and $\ell_2^2$-errors of…

With the advancement of self-supervised learning (SSL), fine-tuning pretrained SSL models for mean opinion score (MOS) prediction has achieved state-of-the-art performance. However, during fine-tuning, these SSL-based MOS prediction models…

We consider a model of selective prediction, where the prediction algorithm is given a data sequence in an online fashion and asked to predict a pre-specified statistic of the upcoming data points. The algorithm is allowed to choose when to…

Differential privacy is a mathematical concept that provides an information-theoretic security guarantee. While differential privacy has emerged as a de facto standard for guaranteeing privacy in data sharing, the known mechanisms to…

A key problem in a variety of applications is that of domain adaptation from a public source domain, for which a relatively large amount of labeled data with no privacy constraints is at one's disposal, to a private target domain, for which…

Private regression has received attention from both database and security communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed the functional mechanism (Zhang et al. VLDB 2012) for training linear regression models…

Personalized speech intelligibility prediction is challenging. Previous approaches have mainly relied on audiograms, which are inherently limited in accuracy as they only capture a listener's hearing threshold for pure tones. Rather than…

Sufficient statistic perturbation (SSP) is a widely used method for differentially private linear regression. SSP adopts a data-independent approach where privacy noise from a simple distribution is added to sufficient statistics. However,…