86 citations · 387 across the 45 of their papers we have counts for
48 papers
Should I use Synthetic Data for That? An Analysis of the Suitability of Synthetic Data for Data Sharing and Augmentation
Bogdan Kulynych, Theresa Stadler, Jean Louis Raisaro +1
Recent advances in generative modelling have led many to see synthetic data as the go-to solution for a range of problems around data access, scarcity, and under-representation. In…
Attack-Aware Noise Calibration for Differential Privacy
Bogdan Kulynych, Juan Felipe Gomez, Georgios Kaissis +2
Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to…
On the Conflict of Robustness and Learning in Collaborative Machine Learning
Mathilde Raynal, Carmela Troncoso
Collaborative Machine Learning (CML) allows participants to jointly train a machine learning model while keeping their training data private. In many scenarios where CML is seen as…
The Fundamental Limits of Least-Privilege Learning
Theresa Stadler, Bogdan Kulynych, Michael C. Gastpar +2
The promise of least-privilege learning -- to find feature representations that are useful for a learning task but prevent inference of any sensitive information unrelated to this…
Janus: Safe Biometric Deduplication for Humanitarian Aid Distribution
Kasra EdalatNejad, Wouter Lueks, Justinas Sukaitis +3
Humanitarian organizations provide aid to people in need. To use their limited budget efficiently, their distribution processes must ensure that legitimate recipients cannot receiv…
Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings
Klim Kireev, Maksym Andriushchenko, Carmela Troncoso +1
Research on adversarial robustness is primarily focused on image and text data. Yet, many scenarios in which lack of robustness can result in serious risks, such as fraud detection…