We study a setting where a data holder wishes to share data with a receiver, without revealing certain summary statistics of the data distribution (e.g., mean, standard deviation). It achieves this by passing the data through a randomization mechanism. We propose summary statistic privacy, a metric for quantifying the privacy risk of such a mechanism based on the worst-case probability of an adversary guessing the distributional secret within some threshold.

We consider the straggler problem in decentralized learning over a logical ring while preserving user data privacy. Especially, we extend the recently proposed framework of differential privacy (DP) amplification by decentralization by Cyffers and Bellet to include overall training latencycomprising both computation and communication latency.

There is an emerging interest in generating robust algorithmic recourse that would remain valid if the model is updated or changed even slightly. Towards finding robust algorithmic recourse (or counterfactual explanations), existing literature often assumes that the original model m and the new model M are bounded in the parameter space, i.e., ||Params(M)-Params(m)||<.>

Machine learning (ML) models used in prediction and classification tasks may display performance disparities across population groups determined by sensitive attributes (e.g., race, sex, age). We consider the problem of evaluating the performance of a fixed ML model across population groups defined by multiple sensitive attributes (e.g., race and sex and age).

We investigate the contraction properties of locally differentially private mechanisms. More specifically, we derive tight upper bounds on the divergence between Pand Qoutput distributions of an -LDP mechanism in terms of a divergence between the corresponding input distributions P and Q, respectively. Our first main technical result presents a sharp upper bound on the χ2-divergence χ2(P||Q) in terms of χ2(P||Q) and . We also show that the same result holds for a large family of divergences, including KL-divergence and squared Hellinger distance.

We study the community detection problem over binary symmetric stochastic block models (SBMs) while preserving the privacy of the individual connections between the vertices.

Detection of sparse signals arises in many modern applications such as signal processing, bioinformatics, finance, and disease surveillance. However, in many of these applications, the data may contain sensitive personal information, which is desirable to be protected during the data analysis. In this article, we consider the problem of (,δ)-differentially private detection of a general sparse mixture with a focus on how privacy affects the detection power.

Over the past two decades, the rise in adoption of neural networks has surged in parallel with their performance. Concurrently, we have observed the inherent fragility of these prediction models: small changes to the inputs can induce classification errors across entire datasets. In the following study, we examine perturbations constrained by the $\ell _{0}$ –norm, a potent attack model in the domains of computer vision, malware detection, and natural language processing.

We consider the problem of computing a function of n variables using noisy queries, where each query is incorrect with some fixed and known probability $p \in (0,1/2)$ . Specifically, we consider the computation of the $\textsf {OR}$ function of n bits (where queries correspond to noisy readings of the bits) and the $\textsf {MAX}$ function of n real numbers (where queries correspond to noisy pairwise comparisons).

Secure aggregation protects the local models of the users in federated learning, by not allowing the server to obtain any information beyond the aggregate model at each iteration. Naively implementing secure aggregation fails to protect the integrity of the aggregate model in the possible presence of a malicious server forging the aggregation result, which motivates verifiable aggregation in federated learning.