arXiv subjects

Ravi Kumar

Publications and source records attributed to Ravi Kumar.

At least 91 records · Page 5Linked to original sources

arXiv2024

Training Differentially Private Ad Prediction Models with Semi-Sensitive Features

Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features. In this setting, a subset of the features is known to the attacker (and thus need not be protected) while the remaining features as well as the label are unknown to the attacker and should be protected by the DP guarantee. This task interpolates between training the model with full DP (where the label and all features should be protected) or with label DP (where all the features are considered known, and only the label should be protected). We present a new algorithm for training DP models with semi-sensitive features. Through an empirical evaluation on real ads datasets, we demonstrate that our algorithm surpasses in utility the baselines of (i) DP stochastic gradient descent (DP-SGD) run on all features (known and unknown), and (ii) a label DP algorithm run only on the known features (while discarding the unknown ones).

cs.LG↗

arXiv2023

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP). In particular, we leverage the trade-offs between bias and variance to construct better label randomizers depending on a privately estimated prior distribution over the labels. We demonstrate that these randomizers achieve state-of-the-art privacy-utility trade-offs on several datasets, highlighting the importance of reducing bias when training neural networks with label DP. We also provide theoretical results shedding light on the structural properties of the optimal unbiased randomizers.

cs.LG↗

arXiv2023

Optimizing Hierarchical Queries for the Attribution Reporting API

We study the task of performing hierarchical queries based on summary reports from the {\em Attribution Reporting API} for ad conversion measurement. We demonstrate that methods from optimization and differential privacy can help cope with the noise introduced by privacy guardrails in the API. In particular, we present algorithms for (i) denoising the API outputs and ensuring consistency across different levels of the tree, and (ii) optimizing the privacy budget across different levels of the tree. We provide an experimental evaluation of the proposed algorithms on public datasets.

cs.DS↗

arXiv2023

Stability of near surface nitrogen vacancy centers using dielectric surface passivation

We study the photo-physical stability of ensemble near-surface nitrogen vacancy (NV) centers in diamond under vacuum and air. The optically detected magnetic resonance contrast of the NV centers was measured following exposure to laser illumination, showing opposing trends in air compared to vacuum (increasing by up to 9% and dropping by up to 25%, respectively). Characterization using Raman and X-ray photoelectron spectroscopies suggests a surface reconstruction: In air, atmospheric oxygen adsorption on surface leads to an increase in NV- fraction, whereas in vacuum, net oxygen desorption increases the NV0 fraction. NV charge state switching is confirmed by photoluminescence spectroscopy. Deposition of ~ 2 nm alumina (Al2O3) over the diamond surface was shown to stabilize the NV charge state under illumination in either environment, attributed to a more stable surface electronegativity. The use of alumina coating on diamond is therefore a promising approach to improve the resilience of NV sensors.

physics.app-ph↗

arXiv2023

Summary Reports Optimization in the Privacy Sandbox Attribution Reporting API

The Privacy Sandbox Attribution Reporting API has been recently deployed by Google Chrome to support the basic advertising functionality of attribution reporting (aka conversion measurement) after deprecation of third-party cookies. The API implements a collection of privacy-enhancing guardrails including contribution bounding and noise injection. It also offers flexibility for the analyst to allocate the contribution budget. In this work, we present methods for optimizing the allocation of the contribution budget for summary reports from the Attribution Reporting API. We evaluate them on real-world datasets as well as on a synthetic data model that we find to accurately capture real-world conversion data. Our results demonstrate that optimizing the parameters that can be set by the analyst can significantly improve the utility achieved by querying the API while satisfying the same privacy bounds.

cs.CR↗

arXiv2023

Sparsity-Preserving Differentially Private Training of Large Embedding Models

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient descent, has been the workhorse in protecting user privacy without compromising model accuracy by much. However, applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. To address this issue, we present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models. Our algorithms achieve substantial reductions ($10^6 \times$) in gradient size, while maintaining comparable levels of accuracy, on benchmark real-world datasets.

cs.LG↗

arXiv2023

Towards Separating Computational and Statistical Differential Privacy

Computational differential privacy (CDP) is a natural relaxation of the standard notion of (statistical) differential privacy (SDP) proposed by Beimel, Nissim, and Omri (CRYPTO 2008) and Mironov, Pandey, Reingold, and Vadhan (CRYPTO 2009). In contrast to SDP, CDP only requires privacy guarantees to hold against computationally-bounded adversaries rather than computationally-unbounded statistical adversaries. Despite the question being raised explicitly in several works (e.g., Bun, Chen, and Vadhan, TCC 2016), it has remained tantalizingly open whether there is any task achievable with the CDP notion but not the SDP notion. Even a candidate such task is unknown. Indeed, it is even unclear what the truth could be! In this work, we give the first construction of a task achievable with the CDP notion but not the SDP notion, under the following strong but plausible cryptographic assumptions: (1) Non-Interactive Witness Indistinguishable Proofs, (2) Laconic Collision-Resistant Keyless Hash Functions, (3) Differing-Inputs Obfuscation for Public-Coin Samplers. In particular, we construct a task for which there exists an $\varepsilon$-CDP mechanism with $\varepsilon = O(1)$ achieving $1-o(1)$ utility, but any $(\varepsilon, δ)$-SDP mechanism, including computationally-unbounded ones, that achieves a constant utility must use either a super-constant $\varepsilon$ or an inverse-polynomially large $δ$. To prove this, we introduce a new approach for showing that a mechanism satisfies CDP: first we show that a mechanism is "private" against a certain class of decision tree adversaries, and then we use cryptographic constructions to "lift" this into privacy against computationally bounded adversaries. We believe this approach could be useful to devise further tasks separating CDP from SDP.

cs.CR↗

arXiv2023

Electrical noise spectroscopy of magnons in a quantum Hall ferromagnet

Collective spin-wave excitations-magnons-in a quantum Hall ferromagnet are promising quasi-particles for next-generation spintronics devices, including platforms for information transfer. Detection of these charge-neutral excitations relies on the conversion of magnons into electrical signals in the form of excess electrons and holes, but if these signals are equal the magnon detection remains elusive. In this work, we overcome this shortcoming by measuring the electrical noise generated by magnons. We use the symmetry-broken quantum Hall ferromagnet of the zeroth Landau level in graphene to launch magnons. Absorption of these magnons creates excess noise above the Zeeman energy and remains finite even when the average electrical signal is zero. Moreover, we formulate a theoretical model in which the noise is generated by equilibration (partial or full, depending on the bias voltage) between edge channels and propagating magnons. Our model, which agrees with experimental observations, also allows us to pinpoint the regime of ballistic magnon transport in our device.

cond-mat.mes-hall↗

arXiv2023

Private Ad Modeling with DP-SGD

A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descent (DP-SGD). While this algorithm has been evaluated on text and image data, it has not been previously applied to ads data, which are notorious for their high class imbalance and sparse gradient updates. In this work we apply DP-SGD to several ad modeling tasks including predicting click-through rates, conversion rates, and number of conversion events, and evaluate their privacy-utility trade-off on real-world datasets. Our work is the first to empirically demonstrate that DP-SGD can provide both privacy and utility for ad modeling tasks.

cs.LG↗

arXiv2023

Regression with Label Differential Privacy

We study the task of training regression models with the guarantee of label differential privacy (DP). Based on a global prior distribution on label values, which could be obtained privately, we derive a label DP randomization mechanism that is optimal under a given regression loss function. We prove that the optimal mechanism takes the form of a "randomized response on bins", and propose an efficient algorithm for finding the optimal bin values. We carry out a thorough experimental evaluation on several datasets demonstrating the efficacy of our algorithm.

cs.LG↗

arXiv2023

User-Level Differential Privacy With Few Examples Per User

Previous work on user-level differential privacy (DP) [Ghazi et al. NeurIPS 2021, Bun et al. STOC 2023] obtained generic algorithms that work for various learning tasks. However, their focus was on the example-rich regime, where the users have so many examples that each user could themselves solve the problem. In this work we consider the example-scarce regime, where each user has only a few examples, and obtain the following results: 1. For approximate-DP, we give a generic transformation of any item-level DP algorithm to a user-level DP algorithm. Roughly speaking, the latter gives a (multiplicative) savings of $O_{\varepsilon,δ}(\sqrt{m})$ in terms of the number of users required for achieving the same utility, where $m$ is the number of examples per user. This algorithm, while recovering most known bounds for specific problems, also gives new bounds, e.g., for PAC learning. 2. For pure-DP, we present a simple technique for adapting the exponential mechanism [McSherry, Talwar FOCS 2007] to the user-level setting. This gives new bounds for a variety of tasks, such as private PAC learning, hypothesis selection, and distribution learning. For some of these problems, we show that our bounds are near-optimal.

cs.DS↗

arXiv2023

Differentially Private Aggregation via Imperfect Shuffling

In this paper, we introduce the imperfect shuffle differential privacy model, where messages sent from users are shuffled in an almost uniform manner before being observed by a curator for private aggregation. We then consider the private summation problem. We show that the standard split-and-mix protocol by Ishai et. al. [FOCS 2006] can be adapted to achieve near-optimal utility bounds in the imperfect shuffle model. Specifically, we show that surprisingly, there is no additional error overhead necessary in the imperfect shuffle model.

cs.CR↗

arXiv2023

Differentially Private Data Release over Multiple Tables

We study synthetic data release for answering multiple linear queries over a set of database tables in a differentially private way. Two special cases have been considered in the literature: how to release a synthetic dataset for answering multiple linear queries over a single table, and how to release the answer for a single counting (join size) query over a set of database tables. Compared to the single-table case, the join operator makes query answering challenging, since the sensitivity (i.e., by how much an individual data record can affect the answer) could be heavily amplified by complex join relationships. We present an algorithm for the general problem, and prove a lower bound illustrating that our general algorithm achieves parameterized optimality (up to logarithmic factors) on some simple queries (e.g., two-table join queries) in the most commonly-used privacy parameter regimes. For the case of hierarchical joins, we present a data partition procedure that exploits the concept of {\em uniformized sensitivities} to further improve the utility.

cs.DB↗

arXiv2023

Ticketed Learning-Unlearning Schemes

We consider the learning--unlearning paradigm defined as follows. First given a dataset, the goal is to learn a good predictor, such as one minimizing a certain loss. Subsequently, given any subset of examples that wish to be unlearnt, the goal is to learn, without the knowledge of the original training dataset, a good predictor that is identical to the predictor that would have been produced when learning from scratch on the surviving examples. We propose a new ticketed model for learning--unlearning wherein the learning algorithm can send back additional information in the form of a small-sized (encrypted) ``ticket'' to each participating training example, in addition to retaining a small amount of ``central'' information for later. Subsequently, the examples that wish to be unlearnt present their tickets to the unlearning algorithm, which additionally uses the central information to return a new predictor. We provide space-efficient ticketed learning--unlearning schemes for a broad family of concept classes, including thresholds, parities, intersection-closed classes, among others. En route, we introduce the count-to-zero problem, where during unlearning, the goal is to simply know if there are any examples that survived. We give a ticketed learning--unlearning scheme for this problem that relies on the construction of Sperner families with certain properties, which might be of independent interest.

cs.LG↗

arXiv2023

Ferrous Metal Matrix Composites Status Scope and Challenges

The present paper is an effort to culminate the status, scopes and challenges in the development of ferrous metal matrix composites (FMMCs). The FMMCs are old but less in use than the non-ferrous metal matrix composites (NFMMCs), as far as literature and actual applications are concerned. Therefore, this stimulates the exploration of the reasons behind the scarcity of literature and field applications of the FMMCs, which must be investigated scientifically. The powder metallurgy route is the most used process for fabricating iron and steel based FMMCs by reinforcing particulates. At the same time, the in-situ method has been used for the fabrication and cast iron-based FMMCs. The main characteristics being considered during the designing and fabrication of FMMCs are wear resistance and improved specific mechanical properties. To fabricate cheaper and eco-friendly FMMCs, traditionally used costly reinforcements such as SiC, WC, TiC, SiO2, TiO2, TiB2 are required to be replaced by inexpensive industrial wastes like red-mud, fly-ashes and grinding swarf. The data extracted from the web of science exhibited that the FMMCs have been researched less than the NFMMCs. The increasing number of research papers on FMMCs indicates a bright future. FMMCs are going to be a favourite topic among researchers and manufacturers. Higher strengths, wear resistance, dimensional stability at elevated temperatures, and, most importantly, the lower cost will put forward the FMMCs as a stiff competitor of NFMMCs. In developing and mass production of FMMCs for field applications, challenges like oxidation and higher weight still require special research efforts.

cond-mat.mtrl-sci↗

arXiv2023

On Differentially Private Sampling from Gaussian and Product Distributions

Given a dataset of $n$ i.i.d. samples from an unknown distribution $P$, we consider the problem of generating a sample from a distribution that is close to $P$ in total variation distance, under the constraint of differential privacy (DP). We study the problem when $P$ is a multi-dimensional Gaussian distribution, under different assumptions on the information available to the DP mechanism: known covariance, unknown bounded covariance, and unknown unbounded covariance. We present new DP sampling algorithms, and show that they achieve near-optimal sample complexity in the first two settings. Moreover, when $P$ is a product distribution on the binary hypercube, we obtain a pure-DP algorithm whereas only an approximate-DP algorithm (with slightly worse sample complexity) was previously known.

cs.DS↗

arXiv2023

Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient

We obtain a new protocol for binary counting in the $\varepsilon$-shuffle-DP model with error $O(1/\varepsilon)$ and expected communication $\tilde{O}\left(\frac{\log n}{\varepsilon}\right)$ messages per user. Previous protocols incur either an error of $O(1/\varepsilon^{1.5})$ with $O_\varepsilon(\log{n})$ messages per user (Ghazi et al., ITC 2020) or an error of $O(1/\varepsilon)$ with $O_\varepsilon(n^{2.5})$ messages per user (Cheu and Yan, TPDP 2022). Using the new protocol, we obtained improved $\varepsilon$-shuffle-DP protocols for real summation and histograms.

cs.DS↗

arXiv2023

Approximating a RUM from Distributions on k-Slates

In this work we consider the problem of fitting Random Utility Models (RUMs) to user choices. Given the winner distributions of the subsets of size $k$ of a universe, we obtain a polynomial-time algorithm that finds the RUM that best approximates the given distribution on average. Our algorithm is based on a linear program that we solve using the ellipsoid method. Given that its corresponding separation oracle problem is NP-hard, we devise an approximate separation oracle that can be viewed as a generalization of the weighted feedback arc set problem to hypergraphs. Our theoretical result can also be made practical: we obtain a heuristic that is effective and scales to real-world datasets.

cs.LG↗