arXiv subjects

Badih Ghazi

Publications and source records attributed to Badih Ghazi.

At least 37 records · Page 2Linked to original sources

arXiv2024

Scalable DP-SGD: Shuffling vs. Poisson Subsampling

We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Batch Linear Queries (ABLQ) mechanism with shuffled batch sampling, demonstrating substantial gaps when compared to Poisson subsampling; prior analysis was limited to a single epoch. Since the privacy analysis of Differentially Private Stochastic Gradient Descent (DP-SGD) is obtained by analyzing the ABLQ mechanism, this brings into serious question the common practice of implementing shuffling-based DP-SGD, but reporting privacy parameters as if Poisson subsampling was used. To understand the impact of this gap on the utility of trained machine learning models, we introduce a practical approach to implement Poisson subsampling at scale using massively parallel computation, and efficiently train models with the same. We compare the utility of models trained with Poisson-subsampling-based DP-SGD, and the optimistic estimates of utility when using shuffling, via our new lower bounds on the privacy guarantee of ABLQ with shuffling.

cs.LG↗

arXiv2024

Differentially Private Optimization with Sparse Gradients

Motivated by applications of large embedding models, we study differentially private (DP) optimization problems under sparsity of individual gradients. We start with new near-optimal bounds for the classic mean estimation problem but with sparse data, improving upon existing algorithms particularly for the high-dimensional regime. Building on this, we obtain pure- and approximate-DP algorithms with almost optimal rates for stochastic convex optimization with sparse gradients; the former represents the first nearly dimension-independent rates for this problem. Finally, we study the approximation of stationary points for the empirical loss in approximate-DP optimization and obtain rates that depend on sparsity instead of dimension, modulo polylogarithmic factors.

cs.LG↗

arXiv2024

Differential Privacy on Trust Graphs

We study differential privacy (DP) in a multi-party setting where each party only trusts a (known) subset of the other parties with its data. Specifically, given a trust graph where vertices correspond to parties and neighbors are mutually trusting, we give a DP algorithm for aggregation with a much better privacy-utility trade-off than in the well-studied local model of DP (where each party trusts no other party). We further study a robust variant where each party trusts all but an unknown subset of at most $t$ of its neighbors (where $t$ is a given parameter), and give an algorithm for this setting. We complement our algorithms with lower bounds, and discuss implications of our work to other tasks in private learning and analytics.

cs.CR↗

arXiv2024

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expose a critical yet underexplored vulnerability in the deployment of unlearning systems: the assumption that the data requested for removal is always part of the original training set. We present a threat model where an attacker can degrade model accuracy by submitting adversarial unlearning requests for data not present in the training set. We propose white-box and black-box attack algorithms and evaluate them through a case study on image classification tasks using the CIFAR-10 and ImageNet datasets, targeting a family of widely used unlearning methods. Our results show extremely poor test accuracy following the attack: 3.6% on CIFAR-10 and 0.4% on ImageNet for white-box attacks, and 8.5% on CIFAR-10 and 1.3% on ImageNet for black-box attacks. Additionally, we evaluate various verification mechanisms to detect the legitimacy of unlearning requests and reveal the challenges in verification, as most of the mechanisms fail to detect stealthy attacks without severely impairing their ability to process valid requests. These findings underscore the urgent need for research on more robust request verification methods and unlearning protocols, should the deployment of machine unlearning systems become more prevalent in the future.

cs.CR↗

arXiv2024

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive data due to potential memorization. While differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit, current evaluations on LLMs mostly treat each example (text record) as the privacy unit. This leads to uneven user privacy guarantees when contributions per user vary. We therefore study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users. We present a systematic evaluation of user-level DP for LLM fine-tuning on natural language generation tasks. Focusing on two mechanisms for achieving user-level DP guarantees, Group Privacy and User-wise DP-SGD, we investigate design choices like data selection strategies and parameter tuning for the best privacy-utility tradeoff.

cs.CL↗

arXiv2024

On Convex Optimization with Semi-Sensitive Features

We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive. This generalizes the Label DP setting where only the label is sensitive. We give improved upper and lower bounds on the excess risk for DP-ERM. In particular, we show that the error only scales polylogarithmically in terms of the sensitive domain size, improving upon previous results that scale polynomially in the sensitive domain size (Ghazi et al., 2021).

cs.LG↗

arXiv2024

On Computing Pairwise Statistics with Local Differential Privacy

We study the problem of computing pairwise statistics, i.e., ones of the form $\binom{n}{2}^{-1} \sum_{i \ne j} f(x_i, x_j)$, where $x_i$ denotes the input to the $i$th user, with differential privacy (DP) in the local model. This formulation captures important metrics such as Kendall's $τ$ coefficient, Area Under Curve, Gini's mean difference, Gini's entropy, etc. We give several novel and generic algorithms for the problem, leveraging techniques from DP algorithms for linear queries.

cs.DS↗

arXiv2024

How Private are DP-SGD Implementations?

We demonstrate a substantial gap between the privacy guarantees of the Adaptive Batch Linear Queries (ABLQ) mechanism under different types of batch sampling: (i) Shuffling, and (ii) Poisson subsampling; the typical analysis of Differentially Private Stochastic Gradient Descent (DP-SGD) follows by interpreting it as a post-processing of ABLQ. While shuffling-based DP-SGD is more commonly used in practical implementations, it has not been amenable to easy privacy analysis, either analytically or even numerically. On the other hand, Poisson subsampling-based DP-SGD is challenging to scalably implement, but has a well-understood privacy analysis, with multiple open-source numerically tight privacy accountants available. This has led to a common practice of using shuffling-based DP-SGD in practice, but using the privacy analysis for the corresponding Poisson subsampling version. Our result shows that there can be a substantial gap between the privacy analysis when using the two types of batch sampling, and thus advises caution in reporting privacy parameters for DP-SGD.

cs.LG↗

arXiv2024

Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization

In this work, we give a new technique for analyzing individualized privacy accounting via the following simple observation: if an algorithm is one-sided add-DP, then its subsampled variant satisfies two-sided DP. From this, we obtain several improved algorithms for private combinatorial optimization problems, including decomposable submodular maximization and set cover. Our error guarantees are asymptotically tight and our algorithm satisfies pure-DP while previously known algorithms (Gupta et al., 2010; Chaturvedi et al., 2021) are approximate-DP. We also show an application of our technique beyond combinatorial optimization by giving a pure-DP algorithm for the shifting heavy hitter problem in a stream; previously, only an approximateDP algorithm was known (Kaplan et al., 2021; Cohen & Lyu, 2023).

cs.DS↗

arXiv2024

Differentially Private Ad Conversion Measurement

In this work, we study ad conversion measurement, a central functionality in digital advertising, where an advertiser seeks to estimate advertiser website (or mobile app) conversions attributed to ad impressions that users have interacted with on various publisher websites (or mobile apps). Using differential privacy (DP), a notion that has gained in popularity due to its strong mathematical guarantees, we develop a formal framework for private ad conversion measurement. In particular, we define the notion of an operationally valid configuration of the attribution rule, DP adjacency relation, contribution bounding scope and enforcement point. We then provide, for the set of configurations that most commonly arises in practice, a complete characterization, which uncovers a delicate interplay between attribution and privacy.

cs.CR↗

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

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

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↗