Search Results for author:
Found 43 papers, 1 papers with code
Learning and Evaluating a Differentially Private Pre-trained Language Model
One method to guarantee the privacy of such individuals is to train a differentially-private language model, but this usually comes at the expense of model performance.
Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold Queries
One of the most basic problems for studying the "price of privacy over time" is the so called private counter problem, introduced by Dwork et al. (2010) and Chan et al. (2010).
Private Truly-Everlasting Robust-Prediction
Importantly, PEP provides privacy both for the initial training set and for the endless stream of classification queries.
Hot PATE: Private Aggregation of Distributions for Diverse Task
Moreover, the knowledge of models is often encapsulated in the response distribution itself and preserving this diversity is critical for fluid and effective knowledge transfer from teachers to student.
On Differentially Private Online Predictions
In this work we introduce an interactive variant of joint differential privacy towards handling online processes in which existing privacy definitions seem too restrictive.
On Differential Privacy and Adaptive Data Analysis with Bounded Space
We study the space complexity of the two related fields of differential privacy and adaptive data analysis.
Concurrent Shuffle Differential Privacy Under Continual Observation
the counter problem) and show that the concurrent shuffle model allows for significantly improved error compared to a standard (single) shuffle model.
Relaxed Models for Adversarial Streaming: The Advice Model and the Bounded Interruptions Model
Streaming algorithms are typically analyzed in the oblivious setting, where we assume that the input stream is fixed in advance.
Differentially-Private Bayes Consistency
We construct a universally Bayes consistent learning rule that satisfies differential privacy (DP).
Õptimal Differentially Private Learning of Thresholds and Quasi-Concave Optimization
The problem of learning threshold functions is a fundamental one in machine learning.
Tricking the Hashing Trick: A Tight Lower Bound on the Robustness of CountSketch to Adaptive Inputs
When inputs are adaptive, however, an adversarial input can be constructed after $O(\ell)$ queries with the classic estimator and the best known robust estimator only supports $\tilde{O}(\ell^2)$ queries.
On the Robustness of CountSketch to Adaptive Inputs
CountSketch is a popular dimensionality reduction technique that maps vectors to a lower dimension using randomized linear measurements.
Monotone Learning
Our transformation readily implies monotone learners in a variety of contexts: for example it extends Pestov's result to classification tasks with an arbitrary number of labels.
Adaptive Data Analysis with Correlated Observations
The vast majority of the work on adaptive data analysis focuses on the case where the samples in the dataset are independent.
Differentially-Private Clustering of Easy Instances
Clustering is a fundamental problem in data analysis.
FriendlyCore: Practical Differentially Private Aggregation
Differentially private algorithms for common metric aggregation tasks, such as clustering or averaging, often have limited practicality due to their complexity or to the large number of data points that is required for accurate results.
Differentially Private Approximate Quantiles
In this work we study the problem of differentially private (DP) quantiles, in which given dataset $X$ and quantiles $q_1, ..., q_m \in [0, 1]$, we want to output $m$ quantile estimations which are as close as possible to the true quantiles and preserve DP.
A Framework for Adversarial Streaming via Differential Privacy and Difference Estimators
Classical streaming algorithms operate under the (not always reasonable) assumption that the input stream is fixed in advance.
On the Sample Complexity of Privately Learning Axis-Aligned Rectangles
We revisit the fundamental problem of learning Axis-Aligned-Rectangles over a finite grid $X^d\subseteq{\mathbb{R}}^d$ with differential privacy.
Differentially Private Multi-Armed Bandits in the Shuffle Model
We give an $(\varepsilon,\delta)$-differentially private algorithm for the multi-armed bandit (MAB) problem in the shuffle model with a distribution-dependent regret of $O\left(\left(\sum_{a\in [k]:\Delta_a>0}\frac{\log T}{\Delta_a}\right)+\frac{k\sqrt{\log\frac{1}{\delta}}\log T}{\varepsilon}\right)$, and a distribution-independent regret of $O\left(\sqrt{kT\log T}+\frac{k\sqrt{\log\frac{1}{\delta}}\log T}{\varepsilon}\right)$, where $T$ is the number of rounds, $\Delta_a$ is the suboptimality gap of the arm $a$, and $k$ is the total number of arms.
Separating Adaptive Streaming from Oblivious Streaming
We present a streaming problem for which every adversarially-robust streaming algorithm must use polynomial space, while there exists a classical (oblivious) streaming algorithm that uses only polylogarithmic space.
Data Structures and Algorithms
Differentially Private Weighted Sampling
A weighted sample of keys by (a function of) frequency is a highly versatile summary that provides a sparse set of representative keys and supports approximate evaluations of query statistics.
The Sparse Vector Technique, Revisited
This simple algorithm privately tests whether the value of a given query on a database is close to what we expect it to be.
On the Round Complexity of the Shuffle Model
Combining this primitive with the two-round semi-honest protocol of Applebaun et al. [TCC 2018], we obtain that every randomized functionality can be computed in the shuffle model with an honest majority, in merely two rounds.
Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity
We present a differentially private learner for halfspaces over a finite grid $G$ in $\mathbb{R}^d$ with sample complexity $\approx d^{2. 5}\cdot 2^{\log^*|G|}$, which improves the state-of-the-art result of [Beimel et al., COLT 2019] by a $d^2$ factor.
Adversarially Robust Streaming Algorithms via Differential Privacy
A streaming algorithm is said to be adversarially robust if its accuracy guarantees are maintained even when the data stream is chosen maliciously, by an adaptive adversary.
How to Find a Point in the Convex Hull Privately
We study the question of how to compute a point in the convex hull of an input set $S$ of $n$ points in ${\mathbb R}^d$ in a differentially private manner.
Closure Properties for Private Classification and Online Prediction
Let~$\cH$ be a class of boolean functions and consider a {\it composed class} $\cH'$ that is derived from~$\cH$ using some arbitrary aggregation rule (for example, $\cH'$ may be the class of all 3-wise majority-votes of functions in $\cH$).
The power of synergy in differential privacy: Combining a small curator with local randomizers
Motivated by the desire to bridge the utility gap between local and trusted curator models of differential privacy for practical applications, we initiate the theoretical study of a hybrid model introduced by "Blender" [Avent et al.,\ USENIX Security '17], in which differentially private protocols of n agents that work in the local-model are assisted by a differentially private curator that has access to the data of m additional users.
Privately Learning Thresholds: Closing the Exponential Gap
This problem has received much attention recently; unlike the non-private case, where the sample complexity is independent of the domain size and just depends on the desired accuracy and confidence, for private learning the sample complexity must depend on the domain size $X$ (even for approximate differential privacy).
Locally Private k-Means Clustering
We design a new algorithm for the Euclidean $k$-means problem that operates in the local model of differential privacy.
Private Center Points and Learning of Halfspaces
The building block for this learner is a differentially private algorithm for locating an approximate center point of $m>\mathrm{poly}(d, 2^{\log^*|X|})$ points -- a high dimensional generalization of the median function.
Differentially Private Learning of Geometric Concepts
We present differentially private efficient algorithms for learning union of polygons in the plane (which are not necessarily convex).
The Limits of Post-Selection Generalization
While statistics and machine learning offers numerous methods for ensuring generalization, these methods often fail in the presence of adaptivity---the common practice in which the choice of analysis depends on previous interactions with the same dataset.
Concentration Bounds for High Sensitivity Functions Through Differential Privacy
We show that differential privacy can be used to prove concentration bounds for such functions in the non-adaptive setting.
Locating a Small Cluster Privately
We present a new algorithm for locating a small cluster of points with differential privacy [Dwork, McSherry, Nissim, and Smith, 2006].
Simultaneous Private Learning of Multiple Concepts
We investigate the direct-sum problem in the context of differentially private PAC learning: What is the sample complexity of solving $k$ learning tasks simultaneously under differential privacy, and how does this cost compare to that of solving $k$ learning tasks without privacy?
Algorithmic Stability for Adaptive Data Analysis
Specifically, suppose there is an unknown distribution $\mathbf{P}$ and a set of $n$ independent samples $\mathbf{x}$ is drawn from $\mathbf{P}$.
Differentially Private Release and Learning of Threshold Functions
Our sample complexity upper and lower bounds also apply to the tasks of learning distributions with respect to Kolmogorov distance and of properly PAC learning thresholds with differential privacy.
On the Generalization Properties of Differential Privacy
Very recently, Bassily et al. presented an improved bound and showed that (a variant of) the private multiplicative weights algorithm can answer $k$ adaptively chosen statistical queries using sample complexity that grows logarithmically in $k$.
Learning Privately with Labeled and Unlabeled Examples
In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction of private learners, in which the sample complexity is (generally) higher than what is needed for non-private learners.
Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
We show that the sample complexity of these tasks under approximate differential privacy can be significantly lower than that under pure differential privacy.
Characterizing the Sample Complexity of Private Learners
Kasiviswanathan et al. gave a generic construction of private learners for (finite) concept classes, with sample complexity logarithmic in the size of the concept class.
