Bogdan Kulynych

According to our database, Bogdan Kulynych authored at least 28 papers between 2017 and 2025.

Collaborative distances:

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

2025

Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy.

Bogdan Kulynych, Juan Felipe Gómez, Georgios Kaissis, Jamie Hayes, Borja Balle, Flávio P. Calmon, Jean Louis Raisaro

CoRR, July, 2025

Statistical Inference for Responsiveness Verification.

Seung Hyun Cheon, Meredith Stewart, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun

CoRR, July, 2025

(ϵ, δ) Considered Harmful: Best Practices for Reporting Differential Privacy Guarantees.

Juan Felipe Gómez, Bogdan Kulynych, Georgios Kaissis, Jamie Hayes, Borja Balle, Antti Honkela

CoRR, March, 2025

Participatory Assessment of Large Language Model Applications in an Academic Medical Center.

Giorgia Carra, Bogdan Kulynych, François Bastardot, Daniel E. Kaufmann, Noémie Boillat-Blanco, Jean Louis Raisaro

CoRR, January, 2025

A scoping review of privacy and utility metrics in medical synthetic data.

Bayrem Kaabachi, Jérémie Despraz, Thierry Meurers, Karen Otte, Mehmed Halilovic, Bogdan Kulynych, Fabian Prasser, Jean Louis Raisaro

npj Digit. Medicine, 2025

Phantom Anonymization: Adversarial testing for membership inference risks in anonymized health data.

Thierry Meurers, Mehmed Halilovic, Karen Otte, Jérémie Despraz, Bayrem Kaabachi, Bogdan Kulynych, Jean Louis Raisaro, Fabian Prasser

Comput. Biol. Medicine, 2025

2024

Attack-Aware Noise Calibration for Differential Privacy.

Bogdan Kulynych, Juan Felipe Gómez, Georgios Kaissis, Flávio P. Calmon, Carmela Troncoso

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Accelerating Clinical Text Annotation in Underrepresented Languages: A Case Study on Text De-Identification.

He A. Xu, Valentin Loftsson, Bogdan Kulynych, Jean Louis Raisaro

Proceedings of the Digital Health and Informatics Innovations for Sustainable Health Care Systems, 2024

Evaluating Synthetic Data Augmentation to Correct for Data Imbalance in Realistic Clinical Prediction Settings.

Bogdan Kulynych, Jérémie Despraz, Christian Simon, Jean Louis Raisaro

Proceedings of the Digital Health and Informatics Innovations for Sustainable Health Care Systems, 2024

Tunable Privacy Risk Evaluation of Generative Adversarial Networks.

Bogdan Kulynych, Jérémie Despraz, Jean Louis Raisaro

Proceedings of the Digital Health and Informatics Innovations for Sustainable Health Care Systems, 2024

The Fundamental Limits of Least-Privilege Learning.

Theresa Stadler, Bogdan Kulynych, Michael Gastpar, Nicolas Papernot, Carmela Troncoso

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

Prediction without Preclusion: Recourse Verification with Reachable Sets.

Avni Kothari, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Adversarial Robustness for Tabular Data through Cost and Utility Awareness.

Klim Kireev, Bogdan Kulynych, Carmela Troncoso

Proceedings of the 30th Annual Network and Distributed System Security Symposium, 2023

Arbitrary Decisions Are a Hidden Cost of Differentially Private Training.

Bogdan Kulynych, Hsiang Hsu, Carmela Troncoso, Flávio P. Calmon

Proceedings of the 2nd European Workshop on Algorithmic Fairness, 2023

2022

Disparate Vulnerability to Membership Inference Attacks.

Bogdan Kulynych, Mohammad Yaghini, Giovanni Cherubin, Michael Veale, Carmela Troncoso

Proc. Priv. Enhancing Technol., 2022

What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning.

Bogdan Kulynych, Yao-Yuan Yang, Yaodong Yu, Jaroslaw Blasiok, Preetum Nakkiran

CoRR, 2022

What You See is What You Get: Principled Deep Learning via Distributional Generalization.

Bogdan Kulynych, Yao-Yuan Yang, Yaodong Yu, Jaroslaw Blasiok, Preetum Nakkiran

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Epidose: A privacy-preserving epidemic dosimeter based on contact tracing.

Diomidis Spinellis, Stefanos Georgiou, Johan Herland, Mathias Payer, Wouter Lueks, Bogdan Kulynych, Filip Muki Dobranic, konasimakopoulos

Dataset, May, 2021

Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks.

Kendra Albert, Maggie K. Delano, Bogdan Kulynych, Ram Shankar Siva Kumar

CoRR, 2021

Exploring Data Pipelines through the Process Lens: a Reference Model forComputer Vision.

Agathe Balayn, Bogdan Kulynych, Seda F. Gürses

CoRR, 2021

2020

POTs: protective optimization technologies.

Bogdan Kulynych, Rebekah Overdorf, Carmela Troncoso, Seda F. Gürses

Proceedings of the FAT* '20: Conference on Fairness, 2020

2019

Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning.

Mohammad Yaghini, Bogdan Kulynych, Carmela Troncoso

CoRR, 2019

zksk: A Library for Composable Zero-Knowledge Proofs.

Wouter Lueks, Bogdan Kulynych, Jules Fasquelle, Simon Le Bail-Collet, Carmela Troncoso

Proceedings of the 18th ACM Workshop on Privacy in the Electronic Society, 2019

2018

Questioning the assumptions behind fairness solutions.

Rebekah Overdorf, Bogdan Kulynych, Ero Balsa, Carmela Troncoso, Seda F. Gürses

CoRR, 2018

Evading classifiers in discrete domains with provable optimality guarantees.

Bogdan Kulynych, Jamie Hayes, Nikita Samarin, Carmela Troncoso

CoRR, 2018

ClaimChain: Improving the Security and Privacy of In-band Key Distribution for Messaging.

Bogdan Kulynych, Wouter Lueks, Marios Isaakidis, George Danezis, Carmela Troncoso

Proceedings of the 2018 Workshop on Privacy in the Electronic Society, 2018

2017

Feature importance scores and lossless feature pruning using Banzhaf power indices.

Bogdan Kulynych, Carmela Troncoso

CoRR, 2017

ClaimChain: Decentralized Public Key Infrastructure.

Bogdan Kulynych, Marios Isaakidis, Carmela Troncoso, George Danezis

CoRR, 2017