9 papers
Training Fair Tabular Foundation Models
Patrik Kenfack, Jesse C. Cresswell, Anthony L. Caterini +2
Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training.…
Model Stealing Through the Lens of Model Multiplicity
Eliott Baltz, Satoshi Hara, Ulrich Aïvodji
Model stealing attacks, where adversaries create high-fidelity surrogate models, are a significant threat to the intellectual property of machine learning services. Conventional wi…
Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data
Maryam Babaei, Yingke Wang, Hadrien Lautraite +3
Counterfactuals are typically used in high-stakes decision areas to explain a machine learning model by showing how changes to the user profiles result in the desired outcome. Howe…
When Interpretability Is Unequally Distributed: Fairness in Hybrid Interpretable Models
Ziba Jabbar Zare, Ulrich Aïvodji, Ulrich Aïvodji +2
Hybrid interpretable models combine a transparent component with a black-box model by assigning some examples to the former and deferring the rest to the latter. While this design…
Test-Time Collective Action: Proxy-Based Perturbations for Correcting Algorithmic Harms
Meghana Bhange, Ulrich Aïvodji, Ulrich Aïvodji +1
When machine learning systems under-perform for particular subgroups, affected users typically have no way to correct these disparities without relying on platform-level fixes. Exi…
Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy
Rushabh Solanki, Meghana Bhange, Ulrich Aïvodji +1
The integration of AI into daily life has generated considerable attention and excitement, while also raising concerns about automating algorithmic harms and re-entrenching existin…