5 papers
Manipulation-Proof Oblivious Audits against Deceptive Model Providers
Augustin Godinot, Sofiane Azogagh, Julien Ferry +1
Audits have emerged as a critical instrument for algorithmic governance, providing a mechanism for external scrutiny and governance of machine learning models. However, ensuring th…
Training Set Reconstruction from Differentially Private Forests: How Effective is DP?
Alice Gorgé, Julien Ferry, Sébastien Gambs +1
Recent research has shown that structured machine learning models such as tree ensembles are vulnerable to privacy attacks targeting their training data. To mitigate these risks, d…
From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
Awa Khouna, Julien Ferry, Thibaut Vidal
The advent of Machine Learning as a Service (MLaaS) has heightened the trade-off between model explainability and security. In particular, explainability techniques, such as counte…
Fairness and Sparsity within Rashomon sets: Enumeration-Free Exploration and Characterization
Lucas Langlade, Julien Ferry, Gabriel Laberge +1
We introduce an enumeration-free method based on mathematical programming to precisely characterize various properties such as fairness or sparsity within the set of "good models",…
Smooth Sensitivity for Learning Differentially-Private yet Accurate Rule Lists
Timothée Ly, Julien Ferry, Marie-José Huguet +2
Differentially-private (DP) mechanisms can be embedded into the design of a machine learning algorithm to protect the resulting model against privacy leakage. However, this often c…