Borja Balle | DeepAI

AI Chat

Featured Co-authors

Doina Precup
141 publications
Pushmeet Kohli
93 publications
Zhiwei Steven Wu
90 publications
Yu-Xiang Wang
85 publications
Akshay Krishnamurthy
75 publications
Nicholas Carlini
63 publications
Peter Kairouz
43 publications
Florian Tramèr
41 publications
M. Pawan Kumar
41 publications
Justin Hsu
32 publications
Eric Wallace
32 publications

∙ 08/21/2023

Unlocking Accuracy and Fairness in Differentially Private Image Classification

Privacy-preserving machine learning aims to train models on private data...

0 Leonard Berrada, et al. ∙

∙ 05/18/2023

Amplification by Shuffling without Shuffling

Motivated by recent developments in the shuffle model of differential pr...

0 Borja Balle, et al. ∙

∙ 02/27/2023

Differentially Private Diffusion Models Generate Useful Synthetic Images

The ability to generate privacy-preserving synthetic versions of sensiti...

3 Sahra Ghalebikesabi, et al. ∙

∙ 02/15/2023

Tight Auditing of Differentially Private Machine Learning

Auditing mechanisms for differential privacy use probabilistic means to ...

0 Milad Nasr, et al. ∙

∙ 01/30/2023

Extracting Training Data from Diffusion Models

Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...

0 Nicholas Carlini, et al. ∙

∙ 04/28/2022

Unlocking High-Accuracy Differentially Private Image Classification through Scale

Differential Privacy (DP) provides a formal privacy guarantee preventing...

0 Soham De, et al. ∙

∙ 01/13/2022

Reconstructing Training Data with Informed Adversaries

Given access to a machine learning model, can an adversary reconstruct t...

11 Borja Balle, et al. ∙

∙ 01/06/2022

Learning to be adversarially robust and differentially private

We study the difficulties in learning that arise from robust and differe...

0 Jamie Hayes, et al. ∙

∙ 12/08/2021

Ethical and social risks of harm from Language Models

This paper aims to help structure the risk landscape associated with lar...

0 Laura Weidinger, et al. ∙

∙ 02/16/2021

A Law of Robustness for Weight-bounded Neural Networks

Robustness of deep neural networks against adversarial perturbations is ...

0 Hisham Husain, et al. ∙

∙ 09/18/2020

Private Reinforcement Learning with PAC and Regret Guarantees

Motivated by high-stakes decision-making domains like personalized medic...

13 Giuseppe Vietri, et al. ∙

∙ 07/13/2020

Privacy Amplification via Random Check-Ins

Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fund...

12 Borja Balle, et al. ∙

∙ 02/03/2020

Private Summation in the Multi-Message Shuffle Model

The shuffle model of differential privacy (Erlingsson et al. SODA 2019; ...

0 Borja Balle, et al. ∙

∙ 10/20/2019

Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations

Accurately learning from user data while providing quantifiable privacy ...

0 Oluwaseyi Feyisetan, et al. ∙

∙ 10/14/2019

Actor Critic with Differentially Private Critic

Reinforcement learning algorithms are known to be sample inefficient, an...

0 Jonathan Lebensold, et al. ∙

∙ 09/24/2019

Improved Summation from Shuffling

A protocol by Ishai et al. (FOCS 2006) showing how to implement distribu...

0 Borja Balle, et al. ∙

∙ 06/20/2019

Differentially Private Summation with Multi-Message Shuffling

In recent work, Cheu et al. (Eurocrypt 2019) proposed a protocol for n-p...

0 Borja Balle, et al. ∙

∙ 05/29/2019

Privacy Amplification by Mixing and Diffusion Mechanisms

A fundamental result in differential privacy states that the privacy gua...

0 Borja Balle, et al. ∙

∙ 05/26/2019

Automatic Discovery of Privacy-Utility Pareto Fronts

Differential privacy is a mathematical framework for privacy-preserving ...

0 Brendan Avent, et al. ∙

∙ 05/24/2019

Hypothesis Testing Interpretations and Renyi Differential Privacy

Differential privacy is the gold standard in data privacy, with applicat...

0 Borja Balle, et al. ∙

∙ 03/26/2019

Privacy-preserving Active Learning on Sensitive Data for User Intent Classification

Active learning holds promise of significantly reducing data annotation ...

0 Oluwaseyi Feyisetan, et al. ∙

∙ 03/07/2019

The Privacy Blanket of the Shuffle Model

This work studies differential privacy in the context of the recently pr...

0 Borja Balle, et al. ∙

∙ 10/17/2018

Hierarchical Methods of Moments

Spectral methods of moments provide a powerful tool for learning the par...

0 Matteo Ruffini, et al. ∙

∙ 07/31/2018

Subsampled Rényi Differential Privacy and Analytical Moments Accountant

We study the problem of subsampling in differential privacy (DP), a ques...

2 Yu-Xiang Wang, et al. ∙

∙ 07/04/2018

Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences

Differential privacy comes equipped with multiple analytical tools for t...

0 Borja Balle, et al. ∙

∙ 05/16/2018

Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising

The Gaussian mechanism is an essential building block used in multitude ...

12 Borja Balle, et al. ∙

∙ 03/07/2016

Differentially Private Policy Evaluation

We present the first differentially private algorithms for reinforcement...

0 Borja Balle, et al. ∙

∙ 06/27/2012

Local Loss Optimization in Operator Models: A New Insight into Spectral Learning

This paper re-visits the spectral method for learning latent variable mo...

0 Borja Balle, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world