| 2026 | NDSS | To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling. | Meenatchi Sundaram Muthu Selva Annamalai, Borja Balle, Jamie Hayes, Emiliano De Cristofaro |
| 2025 | ICLR | DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction. | Xinwei Zhang, Zhiqi Bu, Borja Balle, Mingyi Hong, Meisam Razaviyayn, Vahab Mirrokni |
| 2025 | ICLR | The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD. | Milad Nasr, Thomas Steinke, Borja Balle, Christopher A. Choquette-Choo, Arun Ganesh, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis |
| 2025 | ICML | Scaling Laws for Differentially Private Language Models. | Ryan McKenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, Georgios Kaissis, Ravi Kumar, Ruibo Liu, Da Yu, Chiyuan Zhang |
| 2025 | SP | Hash-Prune-Invert: Improved Differentially Private Heavy-Hitter Detection in the Two-Server Model. | Borja Balle, James Bell-Clark, Albert Cheu, Adri Gascn, Jonathan Katz, Mariana Raykova, Phillipp Schoppmann, Thomas Steinke |
| 2024 | AISTATS | On the Privacy of Selection Mechanisms with Gaussian Noise. | Jonathan Lebensold, Doina Precup, Borja Balle |
| 2024 | CCS | AirGapAgent: Protecting Privacy-Conscious Conversational Agents. | Eugene Bagdasarian, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage |
| 2024 | ICML | Beyond the Calibration Point: Mechanism Comparison in Differential Privacy. | Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert |
| 2023 | CCS | Amplification by Shuffling without Shuffling. | Borja Balle, James Bell, Adri Gascn |
| 2023 | UAI | Mnemonist: Locating Model Parameters that Memorize Training Examples. | Ali Shahin Shamsabadi, Jamie Hayes, Borja Balle, Adrian Weller |
| 2022 | SP | Reconstructing Training Data with Informed Adversaries. | Borja Balle, Giovanni Cherubin, Jamie Hayes |
| 2021 | ICALP | Optimal Spectral-Norm Approximate Minimization of Weighted Finite Automata. | Borja Balle, Clara Lacroce, Prakash Panangaden, Doina Precup, Guillaume Rabusseau |
| 2020 | AISTATS | Hypothesis Testing Interpretations and Renyi Differential Privacy. | Borja Balle, Gilles Barthe, Marco Gaboardi, Justin Hsu, Tetsuya Sato |
| 2020 | AISTATS | Local Differential Privacy for Sampling. | Hisham Husain, Borja Balle, Zac Cranko, Richard Nock |
| 2020 | AISTATS | Model-Agnostic Counterfactual Explanations for Consequential Decisions. | Amir-Hossein Karimi, Gilles Barthe, Borja Balle, Isabel Valera |
| 2020 | CCS | Private Summation in the Multi-Message Shuffle Model. | Borja Balle, James Bell, Adri Gascn, Kobbi Nissim |
| 2020 | ICLR | A Framework for robustness Certification of Smoothed Classifiers using F-Divergences. | Krishnamurthy (Dj) Dvijotham, Jamie Hayes, Borja Balle, J. Zico Kolter, Chongli Qin, Andrs Gyrgy, Kai Xiao, Sven Gowal, Pushmeet Kohli |
| 2020 | ICML | Private Reinforcement Learning with PAC and Regret Guarantees. | Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Zhiwei Steven Wu |
| 2020 | WSDM | Privacy-Preserving Textual Analysis via Calibrated Perturbations. | Oluwaseyi Feyisetan, Borja Balle |
| 2020 | WSDM | Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations. | Oluwaseyi Feyisetan, Borja Balle, Thomas Drake, Tom Diethe |
| 2020 | WSDM | Calibrating Mechanisms for Privacy Preserving Text Analysis. | Oluwaseyi Feyisetan, Borja Balle, Tom Diethe, Thomas Drake |
| 2019 | AISTATS | Subsampled Renyi Differential Privacy and Analytical Moments Accountant. | Yu-Xiang Wang, Borja Balle, Shiva Prasad Kasiviswanathan |
| 2019 | CCS | PPML '19: Privacy Preserving Machine Learning. | Borja Balle, Adri Gascn, Olya Ohrimenko, Mariana Raykova, Phillipp Schoppmann, Carmela Troncoso |
| 2019 | CRYPTO | The Privacy Blanket of the Shuffle Model. | Borja Balle, James Bell, Adri Gascn, Kobbi Nissim |
| 2018 | AAAI | Learning Predictive State Representations From Non-Uniform Sampling. | Yuri Grinberg, Hossein Aboutalebi, Melanie Lyman-Abramovitch, Borja Balle, Doina Precup |
| 2018 | ICML | Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising. | Borja Balle, Yu-Xiang Wang |
| 2017 | ICALP | Bisimulation Metrics for Weighted Automata. | Borja Balle, Pascale Gourdeau, Prakash Panangaden |
| 2017 | ICML | Spectral Learning from a Single Trajectory under Finite-State Policies. | Borja Balle, Odalric-Ambrym Maillard |
| 2016 | AAAI | Multitask Generalized Eigenvalue Program. | Boyu Wang, Joelle Pineau, Borja Balle |
| 2016 | AISTATS | Low-Rank Approximation of Weighted Tree Automata. | Guillaume Rabusseau, Borja Balle, Shay B. Cohen |
| 2016 | ICML | Differentially Private Policy Evaluation. | Borja Balle, Maziar Gomrokchi, Doina Precup |
| 2016 | IJCAI | Learning Multi-Step Predictive State Representations. | Lucas Langer, Borja Balle, Doina Precup |
| 2016 | ICRA | Learning time series models for pedestrian motion prediction. | Chenghui Zhou, Borja Balle, Joelle Pineau |
| 2015 | ALT | On the Rademacher Complexity of Weighted Automata. | Borja Balle, Mehryar Mohri |
| 2015 | LICS | A Canonical Form for Weighted Automata and Applications to Approximate Minimization. | Borja Balle, Prakash Panangaden, Doina Precup |
| 2015 | UAI | Learning and Planning with Timing Information in Markov Decision Processes. | Pierre-Luc Bacon, Borja Balle, Doina Precup |
| 2014 | ICML | Methods of Moments for Learning Stochastic Languages: Unified Presentation and Empirical Comparison. | Borja Balle, William L. Hamilton, Joelle Pineau |
| 2014 | ICML | Spectral Regularization for Max-Margin Sequence Tagging. | Ariadna Quattoni, Borja Balle, Xavier Carreras, Amir Globerson |
| 2012 | EACL | Spectral Learning for Non-Deterministic Dependency Parsing. | Franco M. Luque, Ariadna Quattoni, Borja Balle, Xavier Carreras |
| 2012 | ICML | Local Loss Optimization in Operator Models: A New Insight into Spectral Learning. | Borja Balle, Ariadna Quattoni, Xavier Carreras |
| 2010 | ALT | A Lower Bound for Learning Distributions Generated by Probabilistic Automata. | Borja Balle, Jorge Castro, Ricard Gavald |