Borja Balle

According to our database, Borja Balle authored at least 89 papers between 2008 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD.

Thomas Steinke, Milad Nasr, Arun Ganesh, Borja Balle, Christopher A. Choquette-Choo, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam D. Smith, Andreas Terzis

CoRR, 2024

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction.

Xinwei Zhang, Zhiqi Bu, Borja Balle, Mingyi Hong, Meisam Razaviyayn, Vahab Mirrokni

CoRR, 2024

CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data.

Zhao Cheng, Diane Wan, Matthew Abueg, Sahra Ghalebikesabi, Ren Yi, Eugene Bagdasarian, Borja Balle, Stefan Mellem, Shawn O'Banion

CoRR, 2024

Operationalizing Contextual Integrity in Privacy-Conscious Assistants.

Sahra Ghalebikesabi, Eugene Bagdasaryan, Ren Yi, Itay Yona, Ilia Shumailov, Aneesh Pappu, Chongyang Shi, Laura Weidinger, Robert Stanforth, Leonard Berrada, Pushmeet Kohli, Po-Sen Huang, Borja Balle

CoRR, 2024

Air Gap: Protecting Privacy-Conscious Conversational Agents.

Eugene Bagdasaryan, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage

CoRR, 2024

The Ethics of Advanced AI Assistants.

Iason Gabriel, Arianna Manzini, Geoff Keeling, Lisa Anne Hendricks, Verena Rieser, Hasan Iqbal, Nenad Tomasev, Ira Ktena, Zachary Kenton, Mikel Rodriguez, Seliem El-Sayed, Sasha Brown, Canfer Akbulut, Andrew Trask, Edward Hughes, A. Stevie Bergman, Renee Shelby, Nahema Marchal, Conor Griffin, Juan Mateos-Garcia, Laura Weidinger, Winnie Street, Benjamin Lange, Alex Ingerman, Alison Lentz, Reed Enger, Andrew Barakat, Victoria Krakovna, John Oliver Siy, Zeb Kurth-Nelson, Amanda McCroskery, Vijay Bolina, Harry Law, Murray Shanahan, Lize Alberts, Borja Balle, Sarah de Haas, Yetunde Ibitoye, Allan Dafoe, Beth Goldberg, Sébastien Krier, Alexander Reese, Sims Witherspoon, Will Hawkins, Maribeth Rauh, Don Wallace, Matija Franklin, Josh A. Goldstein, Joel Lehman, Michael Klenk, Shannon Vallor, Courtney Biles, Meredith Ringel Morris, Helen King, Blaise Agüera y Arcas, William Isaac, James Manyika

CoRR, 2024

Beyond the Calibration Point: Mechanism Comparison in Differential Privacy.

Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert

Proceedings of the Forty-first International Conference on Machine Learning, 2024

AirGapAgent: Protecting Privacy-Conscious Conversational Agents.

Eugene Bagdasarian, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage

Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2024

On the Privacy of Selection Mechanisms with Gaussian Noise.

Jonathan Lebensold, Doina Precup, Borja Balle

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Unlocking Accuracy and Fairness in Differentially Private Image Classification.

Leonard Berrada, Soham De, Judy Hanwen Shen, Jamie Hayes, Robert Stanforth, David Stutz, Pushmeet Kohli, Samuel L. Smith, Borja Balle

CoRR, 2023

Optimal Approximate Minimization of One-Letter Weighted Finite Automata.

Clara Lacroce, Borja Balle, Prakash Panangaden, Guillaume Rabusseau

CoRR, 2023

Differentially Private Diffusion Models Generate Useful Synthetic Images.

Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena, Robert Stanforth, Jamie Hayes, Soham De, Samuel L. Smith, Olivia Wiles, Borja Balle

CoRR, 2023

UN Handbook on Privacy-Preserving Computation Techniques.

David W. Archer, Borja de Balle Pigem, Dan Bogdanov, Mark Craddock, Adrià Gascón, Ronald Jansen, Matjaz Jug, Kim Laine, Robert McLellan, Olga Ohrimenko, Mariana Raykova, Andrew Trask, Simon Wardley

CoRR, 2023

Tight Auditing of Differentially Private Machine Learning.

Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis

Proceedings of the 32nd USENIX Security Symposium, 2023

Extracting Training Data from Diffusion Models.

Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace

Proceedings of the 32nd USENIX Security Symposium, 2023

Mnemonist: Locating Model Parameters that Memorize Training Examples.

Ali Shahin Shamsabadi, Jamie Hayes, Borja Balle, Adrian Weller

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Bounding training data reconstruction in DP-SGD.

Jamie Hayes, Borja Balle, Saeed Mahloujifar

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Amplification by Shuffling without Shuffling.

Borja Balle, James Bell, Adrià Gascón

Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

2022

Approximate minimization of weighted tree automata.

Borja Balle, Guillaume Rabusseau

Inf. Comput., 2022

Bisimulation metrics and norms for real-weighted automata.

Borja Balle, Pascale Gourdeau, Prakash Panangaden

Inf. Comput., 2022

Unlocking High-Accuracy Differentially Private Image Classification through Scale.

Soham De, Leonard Berrada, Jamie Hayes, Samuel L. Smith, Borja Balle

CoRR, 2022

Learning to be adversarially robust and differentially private.

Jamie Hayes, Borja Balle, M. Pawan Kumar

CoRR, 2022

Reconstructing Training Data with Informed Adversaries.

Borja Balle, Giovanni Cherubin, Jamie Hayes

Proceedings of the 43rd IEEE Symposium on Security and Privacy, 2022

Taxonomy of Risks posed by Language Models.

Laura Weidinger, Jonathan Uesato, Maribeth Rauh, Conor Griffin, Po-Sen Huang, John Mellor, Amelia Glaese, Myra Cheng, Borja Balle, Atoosa Kasirzadeh, Courtney Biles, Sasha Brown, Zac Kenton, Will Hawkins, Tom Stepleton, Abeba Birhane, Lisa Anne Hendricks, Laura Rimell, William Isaac, Julia Haas, Sean Legassick, Geoffrey Irving, Iason Gabriel

Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

2021

Ethical and social risks of harm from Language Models.

Laura Weidinger, John Mellor, Maribeth Rauh, Conor Griffin, Jonathan Uesato, Po-Sen Huang, Myra Cheng, Mia Glaese, Borja Balle, Atoosa Kasirzadeh, Zac Kenton, Sasha Brown, Will Hawkins, Tom Stepleton, Courtney Biles, Abeba Birhane, Julia Haas, Laura Rimell, Lisa Anne Hendricks, William Isaac, Sean Legassick, Geoffrey Irving, Iason Gabriel

CoRR, 2021

Optimal Spectral-Norm Approximate Minimization of Weighted Finite Automata.

Borja Balle, Clara Lacroce, Prakash Panangaden, Doina Precup, Guillaume Rabusseau

Proceedings of the 48th International Colloquium on Automata, Languages, and Programming, 2021

2020

Secure and Scalable Document Similarity on Distributed Databases: Differential Privacy to the Rescue.

Phillipp Schoppmann, Lennart Vogelsang, Adrià Gascón, Borja Balle

Proc. Priv. Enhancing Technol., 2020

Automatic Discovery of Privacy-Utility Pareto Fronts.

Brendan Avent, Javier González, Tom Diethe, Andrei Paleyes, Borja Balle

Proc. Priv. Enhancing Technol., 2020

Subsampled Rényi Differential Privacy and Analytical Moments Accountant.

Yu-Xiang Wang, Borja Balle, Shiva Prasad Kasiviswanathan

J. Priv. Confidentiality, 2020

Privacy Profiles and Amplification by Subsampling.

Borja Balle, Gilles Barthe, Marco Gaboardi

J. Priv. Confidentiality, 2020

Diameter and Stationary Distribution of Random $r$-Out Digraphs.

Louigi Addario-Berry, Borja Balle, Guillem Perarnau

Electron. J. Comb., 2020

Calibrating Mechanisms for Privacy Preserving Text Analysis.

Oluwaseyi Feyisetan, Borja Balle, Tom Diethe, Thomas Drake

Proceedings of the PrivateNLP 2020: Workshop on Privacy in Natural Language Processing, 2020

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

Oluwaseyi Feyisetan, Borja Balle, Thomas Drake, Tom Diethe

Proceedings of the WSDM '20: The Thirteenth ACM International Conference on Web Search and Data Mining, 2020

Privacy-Preserving Textual Analysis via Calibrated Perturbations.

Oluwaseyi Feyisetan, Borja Balle

Proceedings of the PrivateNLP 2020: Workshop on Privacy in Natural Language Processing, 2020

Privacy Amplification via Random Check-Ins.

Borja Balle, Peter Kairouz, Brendan McMahan, Om Dipakbhai Thakkar, Abhradeep Thakurta

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Private Reinforcement Learning with PAC and Regret Guarantees.

Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Zhiwei Steven Wu

Proceedings of the 37th International Conference on Machine Learning, 2020

A Framework for robustness Certification of Smoothed Classifiers using F-Divergences.

Krishnamurthy (Dj) Dvijotham, Jamie Hayes, Borja Balle, J. Zico Kolter, Chongli Qin, András György, Kai Xiao, Sven Gowal, Pushmeet Kohli

Proceedings of the 8th International Conference on Learning Representations, 2020

Private Summation in the Multi-Message Shuffle Model.

Borja Balle, James Bell, Adrià Gascón, Kobbi Nissim

Proceedings of the CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security, 2020

Model-Agnostic Counterfactual Explanations for Consequential Decisions.

Amir-Hossein Karimi, Gilles Barthe, Borja Balle, Isabel Valera

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Local Differential Privacy for Sampling.

Hisham Husain, Borja Balle, Zac Cranko, Richard Nock

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Hypothesis Testing Interpretations and Renyi Differential Privacy.

Borja Balle, Gilles Barthe, Marco Gaboardi, Justin Hsu, Tetsuya Sato

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Singular value automata and approximate minimization.

Borja Balle, Prakash Panangaden, Doina Precup

Math. Struct. Comput. Sci., 2019

Actor Critic with Differentially Private Critic.

Jonathan Lebensold, William L. Hamilton, Borja Balle, Doina Precup

CoRR, 2019

Improved Summation from Shuffling.

Borja Balle, James Bell, Adrià Gascón, Kobbi Nissim

CoRR, 2019

Differentially Private Summation with Multi-Message Shuffling.

Borja Balle, James Bell, Adrià Gascón, Kobbi Nissim

CoRR, 2019

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

Oluwaseyi Feyisetan, Thomas Drake, Borja Balle, Tom Diethe

CoRR, 2019

Continual Learning in Practice.

Tom Diethe, Tom Borchert, Eno Thereska, Borja Balle, Neil Lawrence

CoRR, 2019

Privacy Amplification by Mixing and Diffusion Mechanisms.

Borja Balle, Gilles Barthe, Marco Gaboardi, Joseph Geumlek

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

The Privacy Blanket of the Shuffle Model.

Borja Balle, James Bell, Adrià Gascón, Kobbi Nissim

Proceedings of the Advances in Cryptology - CRYPTO 2019, 2019

PPML '19: Privacy Preserving Machine Learning.

Borja Balle, Adrià Gascón, Olya Ohrimenko, Mariana Raykova, Phillipp Schoppmann, Carmela Troncoso

Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019

2018

Generalization bounds for learning weighted automata.

Borja Balle, Mehryar Mohri

Theor. Comput. Sci., 2018

Private Nearest Neighbors Classification in Federated Databases.

Phillipp Schoppmann, Adrià Gascón, Borja Balle

IACR Cryptol. ePrint Arch., 2018

Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences.

Borja Balle, Gilles Barthe, Marco Gaboardi

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

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

Borja Balle, Yu-Xiang Wang

Proceedings of the 35th International Conference on Machine Learning, 2018

Learning Predictive State Representations From Non-Uniform Sampling.

Yuri Grinberg, Hossein Aboutalebi, Melanie Lyman-Abramovitch, Borja Balle, Doina Precup

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017

Privacy-Preserving Distributed Linear Regression on High-Dimensional Data.

Adrià Gascón, Phillipp Schoppmann, Borja Balle, Mariana Raykova, Jack Doerner, Samee Zahur, David Evans

Proc. Priv. Enhancing Technol., 2017

Hierarchical Methods of Moments.

Matteo Ruffini, Guillaume Rabusseau, Borja Balle

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Multitask Spectral Learning of Weighted Automata.

Guillaume Rabusseau, Borja Balle, Joelle Pineau

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Spectral Learning from a Single Trajectory under Finite-State Policies.

Borja Balle, Odalric-Ambrym Maillard

Proceedings of the 34th International Conference on Machine Learning, 2017

Bisimulation Metrics for Weighted Automata.

Borja Balle, Pascale Gourdeau, Prakash Panangaden

Proceedings of the 44th International Colloquium on Automata, Languages, and Programming, 2017

2016

Secure Linear Regression on Vertically Partitioned Datasets.

Adrià Gascón, Phillipp Schoppmann, Borja Balle, Mariana Raykova, Jack Doerner, Samee Zahur, David Evans

IACR Cryptol. ePrint Arch., 2016

Generalization Bounds for Weighted Automata.

Borja Balle, Mehryar Mohri

CoRR, 2016

Learning Multi-Step Predictive State Representations.

Lucas Langer, Borja Balle, Doina Precup

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

Learning time series models for pedestrian motion prediction.

Chenghui Zhou, Borja Balle, Joelle Pineau

Proceedings of the 2016 IEEE International Conference on Robotics and Automation, 2016

Differentially Private Policy Evaluation.

Borja Balle, Maziar Gomrokchi, Doina Precup

Proceedings of the 33nd International Conference on Machine Learning, 2016

Results of the Sequence PredIction ChallengE (SPiCe): a Competition on Learning the Next Symbol in a Sequence.

Borja Balle, Rémi Eyraud, Franco M. Luque, Ariadna Quattoni, Sicco Verwer

Proceedings of the 13th International Conference on Grammatical Inference, 2016

Low-Rank Approximation of Weighted Tree Automata.

Guillaume Rabusseau, Borja Balle, Shay B. Cohen

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

Multitask Generalized Eigenvalue Program.

Boyu Wang, Joelle Pineau, Borja Balle

Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

2015

Weighted Tree Automata Approximation by Singular Value Truncation.

Guillaume Rabusseau, Borja Balle, Shay B. Cohen

CoRR, 2015

Learning and Planning with Timing Information in Markov Decision Processes.

Pierre-Luc Bacon, Borja Balle, Doina Precup

Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

A Canonical Form for Weighted Automata and Applications to Approximate Minimization.

Borja Balle, Prakash Panangaden, Doina Precup

Proceedings of the 30th Annual ACM/IEEE Symposium on Logic in Computer Science, 2015

Learning Weighted Automata.

Borja Balle, Mehryar Mohri

Proceedings of the Algebraic Informatics - 6th International Conference, 2015

On the Rademacher Complexity of Weighted Automata.

Borja Balle, Mehryar Mohri

Proceedings of the Algorithmic Learning Theory - 26th International Conference, 2015

2014

Spectral learning of weighted automata - A forward-backward perspective.

Borja Balle, Xavier Carreras, Franco M. Luque, Ariadna Quattoni

Mach. Learn., 2014

Adaptively learning probabilistic deterministic automata from data streams.

Borja Balle, Jorge Castro, Ricard Gavaldà

Mach. Learn., 2014

Spectral Regularization for Max-Margin Sequence Tagging.

Ariadna Quattoni, Borja Balle, Xavier Carreras, Amir Globerson

Proceedings of the 31th International Conference on Machine Learning, 2014

Methods of Moments for Learning Stochastic Languages: Unified Presentation and Empirical Comparison.

Borja Balle, William L. Hamilton, Joelle Pineau

Proceedings of the 31th International Conference on Machine Learning, 2014

2013

Learning finite-state machines: statistical and algorithmic aspects.

Borja Balle

PhD thesis, 2013

Learning probabilistic automata: A study in state distinguishability.

Borja Balle, Jorge Castro, Ricard Gavaldà

Theor. Comput. Sci., 2013

Ergodicity of Random Walks on Random DFA.

Borja Balle

CoRR, 2013

The Architecture of a Churn Prediction System Based on Stream Mining.

Borja Balle, Bernardino Casas, Alex Catarineu, Ricard Gavaldà, David Manzano-Macho

Proceedings of the Artificial Intelligence Research and Development, 2013

2012

Bootstrapping and Learning PDFA in Data Streams.

Borja Balle, Jorge Castro, Ricard Gavaldà

Proceedings of the Eleventh International Conference on Grammatical Inference, 2012

Spectral Learning of General Weighted Automata via Constrained Matrix Completion.

Borja Balle, Mehryar Mohri

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

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

Borja Balle, Ariadna Quattoni, Xavier Carreras

Proceedings of the 29th International Conference on Machine Learning, 2012

Spectral Learning for Non-Deterministic Dependency Parsing.

Franco M. Luque, Ariadna Quattoni, Borja Balle, Xavier Carreras

Proceedings of the EACL 2012, 2012

2011

A Spectral Learning Algorithm for Finite State Transducers.

Borja Balle, Ariadna Quattoni, Xavier Carreras

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2011

2010

Learning PDFA with Asynchronous Transitions.

Borja Balle, Jorge Castro, Ricard Gavaldà

Proceedings of the Grammatical Inference: Theoretical Results and Applications, 2010

A Lower Bound for Learning Distributions Generated by Probabilistic Automata.

Borja Balle, Jorge Castro, Ricard Gavaldà

Proceedings of the Algorithmic Learning Theory, 21st International Conference, 2010

2008

Absolute-Type Shaft Encoding Using LFSR Sequences With a Prescribed Length.

Josep M. Fuertes, Borja Balle, Enric Ventura

IEEE Trans. Instrum. Meas., 2008