142 citations · 842 across the 49 of their papers we have counts for
56 papers
Tight Bounds for Equivalence Testing with Non-Adaptive Conditional Samples
Gautam Kamath
We study distribution testing with access to non-adaptive conditional samples. Specifically, we give tight bounds for equivalence testing, determining whether two unknown distribut…
Not All Learnable Distribution Classes are Privately Learnable
Mark Bun, Gautam Kamath, Argyris Mouzakis +1
We give an example of a class of distributions that is learnable up to constant error in total variation distance with a finite number of samples, but not learnable under $(\vareps…
Private Distribution Learning with Public Data: The View from Sample Compression
Shai Ben-David, Alex Bie, Clément L. Canonne +2
We study the problem of private distribution learning with access to public data. In this setup, which we refer to as public-private learning, the learner is given public and priva…
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Rachel Cummings, Damien Desfontaines, David Evans +21
In this article, we present a detailed review of current practices and state-of-the-art methodologies in the field of differential privacy (DP), with a focus of advancing DP's depl…
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
Yiwei Lu, Gautam Kamath, Yaoliang Yu
Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks…
Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
Xin Gu, Gautam Kamath, Zhiwei Steven Wu
Differentially private stochastic gradient descent privatizes model training by injecting noise into each iteration, where the noise magnitude increases with the number of model pa…
Private GANs, Revisited
Alex Bie, Gautam Kamath, Guojun Zhang
We show that the canonical approach for training differentially private GANs -- updating the discriminator with differentially private stochastic gradient descent (DPSGD) -- can yi…
A Bias-Accuracy-Privacy Trilemma for Statistical Estimation
Gautam Kamath, Argyris Mouzakis, Matthew Regehr +3
Differential privacy (DP) is a rigorous notion of data privacy, used for private statistics. The canonical algorithm for differentially private mean estimation is to first clip the…
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Jimmy Z. Di, Jack Douglas, Jayadev Acharya +2
We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An ad…
Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
Florian Tramèr, Gautam Kamath, Nicholas Carlini
The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of non-private models pretrained on large p…
Robustness Implies Privacy in Statistical Estimation
Samuel B. Hopkins, Gautam Kamath, Mahbod Majid +1
We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to…
Private Estimation with Public Data
Alex Bie, Gautam Kamath, Vikrant Singhal
We initiate the study of differentially private (DP) estimation with access to a small amount of public data. For private estimation of d-dimensional Gaussians, we assume that the…
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
Da Yu, Gautam Kamath, Janardhan Kulkarni +3
Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all d…
New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma
Gautam Kamath, Argyris Mouzakis, Vikrant Singhal
We prove new lower bounds for statistical estimation tasks under the constraint of -differential privacy. First, we provide tight lower bounds for private covaria…
Indiscriminate Data Poisoning Attacks on Neural Networks
Yiwei Lu, Gautam Kamath, Yaoliang Yu
Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention…
Calibration with Privacy in Peer Review
Wenxin Ding, Gautam Kamath, Weina Wang +1
Reviewers in peer review are often miscalibrated: they may be strict, lenient, extreme, moderate, etc. A number of algorithms have previously been proposed to calibrate reviews. Su…
The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection
Shubhankar Mohapatra, Sajin Sasy, Xi He +2
Hyperparameter optimization is a ubiquitous challenge in machine learning, and the performance of a trained model depends crucially upon their effective selection. While a rich set…
Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism
Samuel B. Hopkins, Gautam Kamath, Mahbod Majid
We give the first polynomial-time algorithm to estimate the mean of a -variate probability distribution with bounded covariance from independent samples subject t…
Robust Estimation for Random Graphs
Jayadev Acharya, Ayush Jain, Gautam Kamath +2
We study the problem of robustly estimating the parameter of an Erdős-Rényi random graph on nodes, where a fraction of nodes may be adversarially corrupted. After showi…
A Private and Computationally-Efficient Estimator for Unbounded Gaussians
Gautam Kamath, Argyris Mouzakis, Vikrant Singhal +2
We give the first polynomial-time, polynomial-sample, differentially private estimator for the mean and covariance of an arbitrary Gaussian distribution in $\mat…
Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy
Christian Covington, Xi He, James Honaker +1
We present a method for producing unbiased parameter estimates and valid confidence intervals under the constraints of differential privacy, a formal framework for limiting individ…
Differentially Private Fine-tuning of Language Models
Da Yu, Saurabh Naik, Arturs Backurs +9
We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus…
The Price of Tolerance in Distribution Testing
Clément L. Canonne, Ayush Jain, Gautam Kamath +1
We revisit the problem of tolerant distribution testing. That is, given samples from an unknown distribution over , is it -close to or $\varepsi…
Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
Gautam Kamath, Xingtu Liu, Huanyu Zhang
We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this problem is restricted to the case where th…